Security · For devops and sre engineers

Run trufflehog via the mantistrufflehog MCP server and handle secret findings without ever exposing the raw secret

deonmenezes/mantishack

Review trust boundaries, auth, input handling, secrets, and dependency risk before release.

PacificStudio/openase

Enterprise-review-grade threat model from harness threat-model {path}.

ruvnet/ruflo

Comprehensive security auditing for Clawdbot deployments. An agent skill from aAAaqwq/AGI-Super-Team.

aAAaqwq/AGI-Super-Team

AI Agent 安全开发与防护最佳实践，包含prompt注入防护、代码执行安全、敏感信息保护、合规审计全流程规范. An agent skill from ProgrammerAnthony/Expert-Coding-Harness.

ProgrammerAnthony/Expert-Coding-Harness

Inline orchestration workflow for security vulnerability detection and remediation with Beads integration.

maslennikov-ig/claude-code-orchestrator-kit

安全威胁建模专家 Owner — 当任务涉及权限、认证、授权、输入输出信任边界、密钥策略、审计、攻击面、Webhook/OAuth、敏感操作或用户要求安全专家视角时使用；要求识别滥用路径并绑定缓解验证。

devcodex-labs/devcodex

Runs a guided, end-to-end security review of a Power Pages site and consolidates every finding into one HTML report covering source code and dependencies, the live site, browser headers, firewall…

microsoft/power-platform-skills

Explore GTI relationships for an IOC to discover related entities.

dandye/ai-runbooks

Respond to a malware incident following PICERL methodology. An agent skill from dandye/ai-runbooks.

dandye/ai-runbooks

Respond to a ransomware incident following PICERL methodology.

dandye/ai-runbooks

Triage a security alert or case. An agent skill from dandye/ai-runbooks.

dandye/ai-runbooks

Triage suspicious login alerts like impossible travel, untrusted location, or multiple failures.

dandye/ai-runbooks

当开始新目标、攻击面不清晰、需要资产测绘/信息收集/前端JS分析/接口与敏感信息提取时调用。负责webpack拆解、source map还原、API端点与密钥提取、历史资产发现、高价值入口定位。命中场景：找不到接口、需要找密钥/隐藏功能/旧版本接口、JS加密与签名逻辑需要还原。

zhaji2333/CkSKILLS

Drive responsible disclosure of a proven finding to a CVE. An agent skill from Encod3d-Sec/TORCH.

Encod3d-Sec/TORCH

Evidence hygiene before any FIND moves to Completed or enters a report.

Encod3d-Sec/TORCH

Business-logic flaw hunting - workflow/state bypass, price/quantity tampering, negative/overflow values, coupon/refund abuse, mass assignment, and logic races.

Encod3d-Sec/TORCH

Web cache poisoning + cache deception hunting - unkeyed input poisoning, cache-key analysis, path-confusion deception, header/parameter cloaking.

Encod3d-Sec/TORCH

MCP server attack hunting - tool poisoning, indirect prompt injection via tool output, rug-pull updates, cross-tool shadowing, over-permissioned/excessive-agency tools, lethal trifecta.

Encod3d-Sec/TORCH

HTTP request smuggling / desync hunting - CL.TE, TE.CL, TE.TE, CL.0, and HTTP/2 downgrade.

Encod3d-Sec/TORCH

SQLi and NoSQLi hunting - error-based, boolean-blind, time-based, UNION, NoSQL operator injection.

Encod3d-Sec/TORCH

Finding validation gate - 7-Question triage adapted for FIND schema.

Encod3d-Sec/TORCH

Search, query, and maintain the qmd-indexed wiki - semantic search, keyword search, re-index after adding pages, check index status.

Encod3d-Sec/TORCH

Test LLM-integrated applications against known prompt injection techniques, evasion methods, and attack intents using the Arcanum PI Taxonomy.

OWASP/secure-agent-playbook

Tile two-dimensional torch.gather(dim=1) kernels for Triton-Ascend so the logical grid stays near the physical vector-core count while each program handles multiple batch rows and loops over K.

Krusty84/triton-ascend-agent-dev-kit

A skill your agent uses when the user is deploying or operating the DOCA Argus Service — the packaged BlueField-side runtime-security container that watches the BlueField and attached host for…

NVIDIA/skills

A skill your agent uses when the user is doing hands-on DOCA SHA programming — offloading SHA-1, SHA-256, or SHA-512 hashing onto a BlueField DPU or ConnectX accelerator, picking between one-shot…

NVIDIA/skills

Pre-install security scanner for AI agent skills. An agent skill from sickn33/agentic-awesome-skills.

sickn33/agentic-awesome-skills

Systematic threat modeling skill for applications, APIs, and systems using STRIDE, PASTA, Attack Trees, DREAD, LINDDUN, and OCTAVE.

hardw00t/ai-security-arsenal

Audit an LLM application for indirect prompt injection - compose objective x technique payloads, deliver them through the channels the agent actually reads, and prove impact with an out-of-band…

forefy/.context

A skill your agent uses when an agent says a test, VM, proof, evaluator, or release gate is overloaded, too strict, blocking staging, or causing false positives; split checks by profile, measure the…

AnastasiyaW/codex-claude-code-config

Write a self-contained OpenTaint engine-issue report from an analysis diagnosis or a full-scan failure.

seqra/opentaint

Check for outdated or vulnerable dependencies. An agent skill from enuno/unifi-mcp-server.

enuno/unifi-mcp-server

Harden OpenClaw self-hosted environments with baseline host controls, auth tightening, secret handling, network segmentation, and safe update/rollback workflows.

BagelHole/DevOps-Security-Agent-Skills

Detect XML External Entity (XXE) vulnerabilities in a codebase using a three-phase approach: recon (find XML parsing sites without external-entity hardening), batched verify (trace user input to…

utkusen/sast-skills

Network infrastructure testing - port scanning, DNS attacks, MITM, VLAN hopping, IPv6, SMB/NetBIOS, sniffing, and DoS assessment.

transilienceai/communitytools

Fetches and extracts payloads from PayloadsAllTheThings on demand.

transilienceai/communitytools

Correlation, confidence scoring, and conflict resolution across all tech-stack signals.

transilienceai/communitytools

Infrastructure tech-stack identification — cloud providers, CDN/WAF, DNS services, TLS/CT, DevOps tooling, plus asset discovery (domains, subdomains, IPs).

transilienceai/communitytools

Security-posture and third-party SaaS identification — security headers, CSP, HSTS, email auth, security.txt, plus payments/analytics/auth/CRM/support integrations.

transilienceai/communitytools

NIS2 Directive (EU 2022/2555) compliance for critical infrastructure entities, covering the 10 minimum security measures.

borghei/Claude-Skills

信息安全分析师与软件开发工程师在搭建文档处理流水线时，当需要拦截违规文件或外部URL，请挂载此技能作为强制前置安检，自动输出 pass/reject 判定与详细合规扫描报告，一键守住零信任安全底线。

anbeime/skill

对进入系统的文件或 URL 执行安全与合规扫描，输出 pass/reject 判定与扫描报告，作为所有文档处理的强制前置关卡。

anbeime/skill

Security review checklist for web applications. An agent skill from cohen-liel/hivemind.

cohen-liel/hivemind

Review owned source, configuration and dependency metadata for supported security findings with precise evidence and remediation.

WrongStack/WrongStack

Application security covering input validation, auth, headers, secrets management, and dependency auditing

rohitg00/awesome-claude-code-toolkit

A skill your agent uses when auditing project dependencies for known vulnerabilities, supply chain risk, or provenance issues — covers Go modules, Maven/JVM, and CI integration for automated scanning

Habitat-Thinking/ai-literacy-superpowers

A skill your agent uses when auditing Docker images in this project for CVEs, base image staleness, or remediation recommendations — covers all four TUI images (Go, Python, Kotlin, C)

Habitat-Thinking/ai-literacy-superpowers