Bagman
profbernardoj/everclaw-community-branches
Secure key management for AI agents. An agent skill from profbernardoj/everclaw-community-branches.
Agent skill for security-manager - invoke with $agent-security-manager
$ npx skills add ruvnet/ruflo --skill agent-security-manager -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ruvnet/ruflo agent-security-manager --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/agent-security-manager .claude/skills/agent-security-manager && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agent-security-manager" agent skill from https://github.com/ruvnet/ruflo/tree/main/.agents/skills/agent-security-manager into .claude/skills/agent-security-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-security-manager", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ruvnet/ruflo/tree/main/.agents/skills/agent-security-managerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ruvnet/ruflo --skill agent-security-manager -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ruvnet/ruflo agent-security-manager --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/agent-security-manager .agents/skills/agent-security-manager && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-security-manager" agent skill from https://github.com/ruvnet/ruflo/tree/main/.agents/skills/agent-security-manager into .agents/skills/agent-security-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-security-manager", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ruvnet/ruflo --skill agent-security-manager -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ruvnet/ruflo agent-security-manager --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/agent-security-manager .cursor/skills/agent-security-manager && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-security-manager" agent skill from https://github.com/ruvnet/ruflo/tree/main/.agents/skills/agent-security-manager into .cursor/skills/agent-security-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-security-manager", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ruvnet/ruflo.git --path .agents/skills/agent-security-manager--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ruvnet/ruflo --skill agent-security-manager -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ruvnet/ruflo agent-security-manager --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/agent-security-manager .gemini/skills/agent-security-manager && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-security-manager" agent skill from https://github.com/ruvnet/ruflo/tree/main/.agents/skills/agent-security-manager into .gemini/skills/agent-security-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-security-manager", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ruvnet/ruflo agent-security-managerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ruvnet/ruflo --skill agent-security-manager -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/agent-security-manager .github/skills/agent-security-manager && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-security-manager" agent skill from https://github.com/ruvnet/ruflo/tree/main/.agents/skills/agent-security-manager into .github/skills/agent-security-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-security-manager", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ruvnet/ruflo --skill agent-security-manager -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ruvnet/ruflo agent-security-manager --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/agent-security-manager .opencode/skills/agent-security-manager && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-security-manager" agent skill from https://github.com/ruvnet/ruflo/tree/main/.agents/skills/agent-security-manager into .opencode/skills/agent-security-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-security-manager", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
agent-security-managerAgent skill for security-manager - invoke with $agent-security-manager
Agent Security Manager is an agent skill from ruvnet/ruflo. Agent skill for security-manager - invoke with $agent-security-manager
Its SKILL.md is about 4.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Security, covering Prompt injection and agent security and Cryptography. The repository describes itself as: 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory…. The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit de590e1. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Agent Security Manager loads about 4.9k tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 179 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from ruvnet/ruflo at commit de590e1, republished under its MIT licence (© ruvnet). 179 words, ~4,936 tokens.
.claude/skills/agent-security-manager/SKILL.md (or your agent's skills folder).name: security-manager type: security color: "#F44336" description: Implements comprehensive security mechanisms for distributed consensus protocols capabilities:
Implements comprehensive security mechanisms for distributed consensus protocols with advanced threat detection.
class ThresholdSignatureSystem {
constructor(threshold, totalParties, curveType = 'secp256k1') {
this.t = threshold; // Minimum signatures required
this.n = totalParties; // Total number of parties
this.curve = this.initializeCurve(curveType);
this.masterPublicKey = null;
this.privateKeyShares = new Map();
this.publicKeyShares = new Map();
this.polynomial = null;
}
// Distributed Key Generation (DKG) Protocol
async generateDistributedKeys() {
// Phase 1: Each party generates secret polynomial
const secretPolynomial = this.generateSecretPolynomial();
const commitments = this.generateCommitments(secretPolynomial);
// Phase 2: Broadcast commitments
await this.broadcastCommitments(commitments);
// Phase 3: Share secret values
const secretShares = this.generateSecretShares(secretPolynomial);
await this.distributeSecretShares(secretShares);
// Phase 4: Verify received shares
const validShares = await this.verifyReceivedShares();
// Phase 5: Combine to create master keys
this.masterPublicKey = this.combineMasterPublicKey(validShares);
return {
masterPublicKey: this.masterPublicKey,
privateKeyShare: this.privateKeyShares.get(this.nodeId),
publicKeyShares: this.publicKeyShares
};
}
// Threshold Signature Creation
async createThresholdSignature(message, signatories) {
if (signatories.length < this.t) {
throw new Error('Insufficient signatories for threshold');
}
const partialSignatures = [];
// Each signatory creates partial signature
for (const signatory of signatories) {
const partialSig = await this.createPartialSignature(message, signatory);
partialSignatures.push({
signatory: signatory,
signature: partialSig,
publicKeyShare: this.publicKeyShares.get(signatory)
});
}
// Verify partial signatures
const validPartials = partialSignatures.filter(ps =>
this.verifyPartialSignature(message, ps.signature, ps.publicKeyShare)
);
if (validPartials.length < this.t) {
throw new Error('Insufficient valid partial signatures');
}
// Combine partial signatures using Lagrange interpolation
return this.combinePartialSignatures(message, validPartials.slice(0, this.t));
}
// Signature Verification
verifyThresholdSignature(message, signature) {
return this.curve.verify(message, signature, this.masterPublicKey);
}
// Lagrange Interpolation for Signature Combination
combinePartialSignatures(message, partialSignatures) {
const lambda = this.computeLagrangeCoefficients(
partialSignatures.map(ps => ps.signatory)
);
let combinedSignature = this.curve.infinity();
for (let i = 0; i < partialSignatures.length; i++) {
const weighted = this.curve.multiply(
partialSignatures[i].signature,
lambda[i]
);
combinedSignature = this.curve.add(combinedSignature, weighted);
}
return combinedSignature;
}
}class ZeroKnowledgeProofSystem {
constructor() {
this.curve = new EllipticCurve('secp256k1');
this.hashFunction = 'sha256';
this.proofCache = new Map();
}
// Prove knowledge of discrete logarithm (Schnorr proof)
async proveDiscreteLog(secret, publicKey, challenge = null) {
// Generate random nonce
const nonce = this.generateSecureRandom();
const commitment = this.curve.multiply(this.curve.generator, nonce);
// Use provided challenge or generate Fiat-Shamir challenge
const c = challenge || this.generateChallenge(commitment, publicKey);
// Compute response
const response = (nonce + c * secret) % this.curve.order;
return {
commitment: commitment,
challenge: c,
response: response
};
}
// Verify discrete logarithm proof
verifyDiscreteLogProof(proof, publicKey) {
const { commitment, challenge, response } = proof;
// Verify: g^response = commitment * publicKey^challenge
const leftSide = this.curve.multiply(this.curve.generator, response);
const rightSide = this.curve.add(
commitment,
this.curve.multiply(publicKey, challenge)
);
return this.curve.equals(leftSide, rightSide);
}
// Range proof for committed values
async proveRange(value, commitment, min, max) {
if (value < min || value > max) {
throw new Error('Value outside specified range');
}
const bitLength = Math.ceil(Math.log2(max - min + 1));
const bits = this.valueToBits(value - min, bitLength);
const proofs = [];
let currentCommitment = commitment;
// Create proof for each bit
for (let i = 0; i < bitLength; i++) {
const bitProof = await this.proveBit(bits[i], currentCommitment);
proofs.push(bitProof);
// Update commitment for next bit
currentCommitment = this.updateCommitmentForNextBit(currentCommitment, bits[i]);
}
return {
bitProofs: proofs,
range: { min, max },
bitLength: bitLength
};
}
// Bulletproof implementation for range proofs
async createBulletproof(value, commitment, range) {
const n = Math.ceil(Math.log2(range));
const generators = this.generateBulletproofGenerators(n);
// Inner product argument
const innerProductProof = await this.createInnerProductProof(
value, commitment, generators
);
return {
type: 'bulletproof',
commitment: commitment,
proof: innerProductProof,
generators: generators,
range: range
};
}
}class ConsensusSecurityMonitor {
constructor() {
this.attackDetectors = new Map();
this.behaviorAnalyzer = new BehaviorAnalyzer();
this.reputationSystem = new ReputationSystem();
this.alertSystem = new SecurityAlertSystem();
this.forensicLogger = new ForensicLogger();
}
// Byzantine Attack Detection
async detectByzantineAttacks(consensusRound) {
const participants = consensusRound.participants;
const messages = consensusRound.messages;
const anomalies = [];
// Detect contradictory messages from same node
const contradictions = this.detectContradictoryMessages(messages);
if (contradictions.length > 0) {
anomalies.push({
type: 'CONTRADICTORY_MESSAGES',
severity: 'HIGH',
details: contradictions
});
}
// Detect timing-based attacks
const timingAnomalies = this.detectTimingAnomalies(messages);
if (timingAnomalies.length > 0) {
anomalies.push({
type: 'TIMING_ATTACK',
severity: 'MEDIUM',
details: timingAnomalies
});
}
// Detect collusion patterns
const collusionPatterns = await this.detectCollusion(participants, messages);
if (collusionPatterns.length > 0) {
anomalies.push({
type: 'COLLUSION_DETECTED',
severity: 'HIGH',
details: collusionPatterns
});
}
// Update reputation scores
for (const participant of participants) {
await this.reputationSystem.updateReputation(
participant,
anomalies.filter(a => a.details.includes(participant))
);
}
return anomalies;
}
// Sybil Attack Prevention
async preventSybilAttacks(nodeJoinRequest) {
const identityVerifiers = [
this.verifyProofOfWork(nodeJoinRequest),
this.verifyStakeProof(nodeJoinRequest),
this.verifyIdentityCredentials(nodeJoinRequest),
this.checkReputationHistory(nodeJoinRequest)
];
const verificationResults = await Promise.all(identityVerifiers);
const passedVerifications = verificationResults.filter(r => r.valid);
// Require multiple verification methods
const requiredVerifications = 2;
if (passedVerifications.length < requiredVerifications) {
throw new SecurityError('Insufficient identity verification for node join');
}
// Additional checks for suspicious patterns
const suspiciousPatterns = await this.detectSybilPatterns(nodeJoinRequest);
if (suspiciousPatterns.length > 0) {
await this.alertSystem.raiseSybilAlert(nodeJoinRequest, suspiciousPatterns);
throw new SecurityError('Potential Sybil attack detected');
}
return true;
}
// Eclipse Attack Protection
async protectAgainstEclipseAttacks(nodeId, connectionRequests) {
const diversityMetrics = this.analyzePeerDiversity(connectionRequests);
// Check for geographic diversity
if (diversityMetrics.geographicEntropy < 2.0) {
await this.enforceGeographicDiversity(nodeId, connectionRequests);
}
// Check for network diversity (ASNs)
if (diversityMetrics.networkEntropy < 1.5) {
await this.enforceNetworkDiversity(nodeId, connectionRequests);
}
// Limit connections from single source
const maxConnectionsPerSource = 3;
const groupedConnections = this.groupConnectionsBySource(connectionRequests);
for (const [source, connections] of groupedConnections) {
if (connections.length > maxConnectionsPerSource) {
await this.alertSystem.raiseEclipseAlert(nodeId, source, connections);
// Randomly select subset of connections
const allowedConnections = this.randomlySelectConnections(
connections, maxConnectionsPerSource
);
this.blockExcessConnections(
connections.filter(c => !allowedConnections.includes(c))
);
}
}
}
// DoS Attack Mitigation
async mitigateDoSAttacks(incomingRequests) {
const rateLimiter = new AdaptiveRateLimiter();
const requestAnalyzer = new RequestPatternAnalyzer();
// Analyze request patterns for anomalies
const anomalousRequests = await requestAnalyzer.detectAnomalies(incomingRequests);
if (anomalousRequests.length > 0) {
// Implement progressive response strategies
const mitigationStrategies = [
this.applyRateLimiting(anomalousRequests),
this.implementPriorityQueuing(incomingRequests),
this.activateCircuitBreakers(anomalousRequests),
this.deployTemporaryBlacklisting(anomalousRequests)
];
await Promise.all(mitigationStrategies);
}
return this.filterLegitimateRequests(incomingRequests, anomalousRequests);
}
}class SecureKeyManager {
constructor() {
this.keyStore = new EncryptedKeyStore();
this.rotationScheduler = new KeyRotationScheduler();
this.distributionProtocol = new SecureDistributionProtocol();
this.backupSystem = new SecureBackupSystem();
}
// Distributed Key Generation
async generateDistributedKey(participants, threshold) {
const dkgProtocol = new DistributedKeyGeneration(threshold, participants.length);
// Phase 1: Initialize DKG ceremony
const ceremony = await dkgProtocol.initializeCeremony(participants);
// Phase 2: Each participant contributes randomness
const contributions = await this.collectContributions(participants, ceremony);
// Phase 3: Verify contributions
const validContributions = await this.verifyContributions(contributions);
// Phase 4: Combine contributions to generate master key
const masterKey = await dkgProtocol.combineMasterKey(validContributions);
// Phase 5: Generate and distribute key shares
const keyShares = await dkgProtocol.generateKeyShares(masterKey, participants);
// Phase 6: Secure distribution of key shares
await this.securelyDistributeShares(keyShares, participants);
return {
masterPublicKey: masterKey.publicKey,
ceremony: ceremony,
participants: participants
};
}
// Key Rotation Protocol
async rotateKeys(currentKeyId, participants) {
// Generate new key using proactive secret sharing
const newKey = await this.generateDistributedKey(participants, Math.floor(participants.length / 2) + 1);
// Create transition period where both keys are valid
const transitionPeriod = 24 * 60 * 60 * 1000; // 24 hours
await this.scheduleKeyTransition(currentKeyId, newKey.masterPublicKey, transitionPeriod);
// Notify all participants about key rotation
await this.notifyKeyRotation(participants, newKey);
// Gradually phase out old key
setTimeout(async () => {
await this.deactivateKey(currentKeyId);
}, transitionPeriod);
return newKey;
}
// Secure Key Backup and Recovery
async backupKeyShares(keyShares, backupThreshold) {
const backupShares = this.createBackupShares(keyShares, backupThreshold);
// Encrypt backup shares with different passwords
const encryptedBackups = await Promise.all(
backupShares.map(async (share, index) => ({
id: `backup_${index}`,
encryptedShare: await this.encryptBackupShare(share, `password_${index}`),
checksum: this.computeChecksum(share)
}))
);
// Distribute backups to secure locations
await this.distributeBackups(encryptedBackups);
return encryptedBackups.map(backup => ({
id: backup.id,
checksum: backup.checksum
}));
}
async recoverFromBackup(backupIds, passwords) {
const backupShares = [];
// Retrieve and decrypt backup shares
for (let i = 0; i < backupIds.length; i++) {
const encryptedBackup = await this.retrieveBackup(backupIds[i]);
const decryptedShare = await this.decryptBackupShare(
encryptedBackup.encryptedShare,
passwords[i]
);
// Verify integrity
const checksum = this.computeChecksum(decryptedShare);
if (checksum !== encryptedBackup.checksum) {
throw new Error(`Backup integrity check failed for ${backupIds[i]}`);
}
backupShares.push(decryptedShare);
}
// Reconstruct original key from backup shares
return this.reconstructKeyFromBackup(backupShares);
}
}// Store security metrics in memory
await this.mcpTools.memory_usage({
action: 'store',
key: `security_metrics_${Date.now()}`,
value: JSON.stringify({
attacksDetected: this.attacksDetected,
reputationScores: Array.from(this.reputationSystem.scores.entries()),
keyRotationEvents: this.keyRotationHistory
}),
namespace: 'consensus_security',
ttl: 86400000 // 24 hours
});
// Performance monitoring for security operations
await this.mcpTools.metrics_collect({
components: [
'signature_verification_time',
'zkp_generation_time',
'attack_detection_latency',
'key_rotation_overhead'
]
});// Learn attack patterns
await this.mcpTools.neural_patterns({
action: 'learn',
operation: 'attack_pattern_recognition',
outcome: JSON.stringify({
attackType: detectedAttack.type,
patterns: detectedAttack.patterns,
mitigation: appliedMitigation
})
});
// Predict potential security threats
const threatPrediction = await this.mcpTools.neural_predict({
modelId: 'security_threat_model',
input: JSON.stringify(currentSecurityMetrics)
});class ByzantineConsensusSecurityWrapper {
constructor(byzantineCoordinator, securityManager) {
this.consensus = byzantineCoordinator;
this.security = securityManager;
}
async secureConsensusRound(proposal) {
// Pre-consensus security checks
await this.security.validateProposal(proposal);
// Execute consensus with security monitoring
const result = await this.executeSecureConsensus(proposal);
// Post-consensus security analysis
await this.security.analyzeConsensusRound(result);
return result;
}
async executeSecureConsensus(proposal) {
// Sign proposal with threshold signature
const signedProposal = await this.security.thresholdSignature.sign(proposal);
// Monitor consensus execution for attacks
const monitor = this.security.startConsensusMonitoring();
try {
// Execute Byzantine consensus
const result = await this.consensus.initiateConsensus(signedProposal);
// Verify result integrity
await this.security.verifyConsensusResult(result);
return result;
} finally {
monitor.stop();
}
}
}class ConsensusPenetrationTester {
constructor(securityManager) {
this.security = securityManager;
this.testScenarios = new Map();
this.vulnerabilityDatabase = new VulnerabilityDatabase();
}
async runSecurityTests() {
const testResults = [];
// Test 1: Byzantine attack simulation
testResults.push(await this.testByzantineAttack());
// Test 2: Sybil attack simulation
testResults.push(await this.testSybilAttack());
// Test 3: Eclipse attack simulation
testResults.push(await this.testEclipseAttack());
// Test 4: DoS attack simulation
testResults.push(await this.testDoSAttack());
// Test 5: Cryptographic security tests
testResults.push(await this.testCryptographicSecurity());
return this.generateSecurityReport(testResults);
}
async testByzantineAttack() {
// Simulate malicious nodes sending contradictory messages
const maliciousNodes = this.createMaliciousNodes(3);
const attack = new ByzantineAttackSimulator(maliciousNodes);
const startTime = Date.now();
const detectionTime = await this.security.detectByzantineAttacks(attack.execute());
const endTime = Date.now();
return {
test: 'Byzantine Attack',
detected: detectionTime !== null,
detectionLatency: detectionTime ? endTime - startTime : null,
mitigation: await this.security.mitigateByzantineAttack(attack)
};
}
}This security manager provides comprehensive protection for distributed consensus protocols with enterprise-grade cryptographic security, advanced threat detection, and robust key management capabilities.
© ruvnet, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/agent-security-manager of ruvnet/ruflo.
Open the folder on GitHubat commit de590e1
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in ruvnet/ruflo, which our catalogue first saw on October 7, 2026.
Agent Security Manager next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Security Manager this skillruvnet/ruflo | 74k | 2 repos | ~4.9k | Automated safety check: Pass | MIT | |
| Bagmanprofbernardoj/everclaw-community-branches | 112 | — | ~4.4k | Automated safety check: Warn | MIT | |
| BagmanLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.9k | Automated safety check: Notes | MIT | |
| Skill Scannergetsentry/skills | 1k | 4 repos | ~2.5k | Automated safety check: Warn | Apache-2.0 | |
| Forensifyalexgreensh/repo-forensics | 187 | — | ~2.5k | Automated safety check: Notes | Custom licence | |
| Hol Guardhashgraph-online/hol-guard | 797 | — | ~542 | Automated safety check: Pass | Apache-2.0 |
profbernardoj/everclaw-community-branches
Secure key management for AI agents. An agent skill from profbernardoj/everclaw-community-branches.
LeoYeAI/openclaw-master-skills
Secure key management for AI agents. An agent skill from LeoYeAI/openclaw-master-skills.
getsentry/skills
Scan agent skills for security issues. An agent skill from getsentry/skills.
alexgreensh/repo-forensics
Cross-agent self-inspection of your AI-agent stack. An agent skill from alexgreensh/repo-forensics.
hashgraph-online/hol-guard
Run HOL Guard scanner and guard operations via uv run hol-guard.
cdppcorp/KESE-KIT
Run a pre-deployment security compliance checklist based on KISA guidelines.
ruvnet/ruflo
Stores, searches, and retrieves successful patterns with HNSW-indexed semantic search so agents can reuse past solutions instead of relearning them.
ruvnet/ruflo
Runs claude-flow CLI security scans for input validation, path traversal, SQL injection, XSS, hardcoded secrets and known CVEs, and writes an audit report.
ruvnet/ruflo
Applies the SPARC method (specification, pseudocode, architecture, refinement, completion) with 17 specialized modes and multi-agent orchestration, from research to deployment.
ruvnet/ruflo
Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.
ruvnet/ruflo
Sets up and drives Ruflo, an npm-installed orchestration layer for multi-agent swarms, persistent memory, routing, hooks and its MCP tool catalog.
ruvnet/ruflo
Reference for spawning, listing, monitoring and stopping agents with claude-flow commands, with agent type families, routing codes and coordination tips.
Categories
Agent skill for security-manager - invoke with $agent-security-manager. Agent Security Manager is an agent skill from ruvnet/ruflo.
Agent Security Manager fits situations like: tasks that involve Prompt injection and agent security; tasks that involve Cryptography.
Run `npx skills add ruvnet/ruflo --skill agent-security-manager -a claude-code`. Or copy the skill folder (.agents/skills/agent-security-manager in ruvnet/ruflo) into .claude/skills/agent-security-manager in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ruvnet/ruflo --skill agent-security-manager -a codex`. Or copy the skill folder (.agents/skills/agent-security-manager in ruvnet/ruflo) into .agents/skills/agent-security-manager in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ruvnet/ruflo --skill agent-security-manager -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-security-manager, .gemini/skills/agent-security-manager, .github/skills/agent-security-manager and .opencode/skills/agent-security-manager in your project.
SKILL.md names no scripts, command-line tools or credentials: Agent Security Manager is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Agent Security Manager is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.9k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Agent Security Manager: Bagman (profbernardoj/everclaw-community-branches, 112 stars), Bagman (LeoYeAI/openclaw-master-skills, 2.2k stars), Skill Scanner (getsentry/skills, 1k stars) and Forensify (alexgreensh/repo-forensics, 187 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ruvnet (a GitHub user) maintains it in ruvnet/ruflo, which has 74,012 GitHub stars. The repository holds 264 skills in this directory. The repository was last updated on October 7, 2026.
Source: ruvnet/ruflo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.