Agent Red Teaming
seb1n/awesome-ai-agent-skills
Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings.
Agent skill
Deploys deception technology including honeypots, honeytokens, and decoy systems to detect attackers who have bypassed perimeter defenses, providing high-fidelity alerts with near-zero false…
The automated check flagged lines worth reading first. See the safety section below.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill performing-deception-technology-deployment -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills performing-deception-technology-deployment --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/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/performing-deception-technology-deployment .claude/skills/performing-deception-technology-deployment && 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 "performing-deception-technology-deployment" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-deception-technology-deployment into .claude/skills/performing-deception-technology-deployment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performing-deception-technology-deployment", 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/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-deception-technology-deploymentType 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 mukul975/Anthropic-Cybersecurity-Skills --skill performing-deception-technology-deployment -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills performing-deception-technology-deployment --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/performing-deception-technology-deployment .agents/skills/performing-deception-technology-deployment && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "performing-deception-technology-deployment" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-deception-technology-deployment into .agents/skills/performing-deception-technology-deployment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performing-deception-technology-deployment", 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 mukul975/Anthropic-Cybersecurity-Skills --skill performing-deception-technology-deployment -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills performing-deception-technology-deployment --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/performing-deception-technology-deployment .cursor/skills/performing-deception-technology-deployment && 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 "performing-deception-technology-deployment" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-deception-technology-deployment into .cursor/skills/performing-deception-technology-deployment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performing-deception-technology-deployment", 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/mukul975/Anthropic-Cybersecurity-Skills.git --path skills/performing-deception-technology-deployment--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 mukul975/Anthropic-Cybersecurity-Skills --skill performing-deception-technology-deployment -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills performing-deception-technology-deployment --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/performing-deception-technology-deployment .gemini/skills/performing-deception-technology-deployment && 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 "performing-deception-technology-deployment" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-deception-technology-deployment into .gemini/skills/performing-deception-technology-deployment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performing-deception-technology-deployment", 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 mukul975/Anthropic-Cybersecurity-Skills performing-deception-technology-deploymentInstalls 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 mukul975/Anthropic-Cybersecurity-Skills --skill performing-deception-technology-deployment -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/performing-deception-technology-deployment .github/skills/performing-deception-technology-deployment && 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 "performing-deception-technology-deployment" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-deception-technology-deployment into .github/skills/performing-deception-technology-deployment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performing-deception-technology-deployment", 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 mukul975/Anthropic-Cybersecurity-Skills --skill performing-deception-technology-deployment -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills performing-deception-technology-deployment --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/performing-deception-technology-deployment .opencode/skills/performing-deception-technology-deployment && 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 "performing-deception-technology-deployment" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-deception-technology-deployment into .opencode/skills/performing-deception-technology-deployment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performing-deception-technology-deployment", 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.
performing-deception-technology-deploymentDeploys deception technology including honeypots, honeytokens, and decoy systems to detect attackers who have bypassed perimeter defenses, providing high-fidelity alerts with near-zero false…
Performing Deception Technology Deployment is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Deploys deception technology including honeypots, honeytokens, and decoy systems to detect attackers who have bypassed perimeter defenses, providing high-fidelity alerts with near-zero false positive rates. Use when SOC teams need early warning of lateral movement, credential abuse, or internal reconnaissance by deploying convincing traps across the network.
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/api-reference.md` and `scripts/agent.py`).
It sits in Security, covering Deployment, Red teaming and adversary simulation and Security operations. The repository describes itself as: 817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io…. The licence is Apache-2.0.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 54a7988. 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.
Ships 1 file in scripts/ (Python), which the agent can run.
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.
Performing Deception Technology Deployment loads about 2.8k tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 101 tokens; SKILL.md has 530 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 patterns that need a careful read before installing.
o": "Canary AWS key in developer laptop .aws/credentials"# Plant in .aws/credentials on developer workstationsAutomated 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); the scripts in this folder are not scanned.
The full file from mukul975/Anthropic-Cybersecurity-Skills at commit 54a7988, republished under its Apache-2.0 licence (© mukul975). 530 words, ~2,801 tokens.
.claude/skills/performing-deception-technology-deployment/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Use this skill when:
Do not use as a replacement for fundamental security controls (patching, EDR, network segmentation) — deception is a detection layer, not a prevention mechanism.
Identify high-value network segments where attackers would traverse:
DECEPTION DEPLOYMENT MAP
━━━━━━━━━━━━━━━━━━━━━━━━
Segment Decoy Type Rationale
Server VLAN Fake file server Attackers enumerate SMB shares during recon
Database VLAN Fake DB server SQL scanning detected in past incidents
AD/DC Segment Honeytoken account Credential theft detection
Executive Subnet Fake workstation Targeted attacks pivot through exec systems
DMZ Honeypot web app External attacker detection
OT Network Fake PLC/HMI Industrial threat detection
Cloud (AWS VPC) Canary EC2 + S3 Cloud lateral movement detectionConfigure Canary devices mimicking real infrastructure:
Windows File Server Canary:
{
"device_name": "FILESERVER-BK04",
"personality": "windows-server-2019",
"services": {
"smb": {
"enabled": true,
"shares": ["Finance_Backup", "HR_Archive", "IT_Docs"],
"files": [
{"name": "Q4_Revenue_2024.xlsx", "alert_on": "read"},
{"name": "employee_ssn_export.csv", "alert_on": "read"},
{"name": "admin_passwords.kdbx", "alert_on": "read"}
]
},
"rdp": {"enabled": true},
"http": {"enabled": false}
},
"network": {
"ip": "10.0.5.200",
"hostname": "FILESERVER-BK04",
"domain": "company.local"
},
"alert_webhook": "https://soar.company.com/api/webhook/canary"
}Database Server Canary:
{
"device_name": "DB-ARCHIVE-02",
"personality": "linux-mysql",
"services": {
"mysql": {
"enabled": true,
"port": 3306,
"databases": ["customer_pii", "payment_archive"],
"alert_on_login_attempt": true
},
"ssh": {
"enabled": true,
"port": 22,
"alert_on_login_attempt": true
}
},
"network": {
"ip": "10.0.10.50",
"hostname": "db-archive-02"
}
}Create fake privileged accounts that should never be used:
# Create honeytoken service account
New-ADUser -Name "svc_sql_backup" `
-SamAccountName "svc_sql_backup" `
-UserPrincipalName "svc_sql_backup@company.local" `
-Description "SQL Backup Service Account - DO NOT DELETE" `
-AccountPassword (ConvertTo-SecureString "FakeP@ssw0rd2024!" -AsPlainText -Force) `
-Enabled $true `
-PasswordNeverExpires $true `
-CannotChangePassword $true
# Add to a group that looks attractive (but monitor for any use)
Add-ADGroupMember -Identity "Domain Admins" -Members "svc_sql_backup"
# Place cached credentials on decoy workstation
# (Mimikatz/credential dumping will find these)
cmdkey /add:fileserver-bk04.company.local /user:company\svc_sql_backup /pass:FakeP@ssw0rd2024!Monitor honeytoken usage in Splunk:
index=wineventlog sourcetype="WinEventLog:Security"
(EventCode=4624 OR EventCode=4625 OR EventCode=4648 OR EventCode=4768 OR EventCode=4769)
TargetUserName="svc_sql_backup"
| eval alert_severity = "CRITICAL"
| eval alert_message = "HONEYTOKEN ACCOUNT USED — Likely credential theft detected"
| table _time, EventCode, src_ip, ComputerName, TargetUserName, Logon_Type, alert_messagePlant tracked documents that beacon when opened:
Canary Document (Word doc with tracking):
# Using Thinkst Canary API to create a canary token document
import requests
response = requests.post(
"https://YOURCOMPANY.canary.tools/api/v1/canarytoken/create",
data={
"auth_token": "YOUR_API_TOKEN",
"kind": "doc-msword",
"memo": "Finance backup folder canary document",
"flock_id": "flock:default"
}
)
token = response.json()
download_url = token["canarytoken"]["canarytoken_url"]
print(f"Download canary doc: {download_url}")
# Place this document in honeypot SMB shares and sensitive directoriesAWS Canary Token (S3 access key):
# Create AWS canary token — alerts when access key is used
response = requests.post(
"https://YOURCOMPANY.canary.tools/api/v1/canarytoken/create",
data={
"auth_token": "YOUR_API_TOKEN",
"kind": "aws-id",
"memo": "Canary AWS key in developer laptop .aws/credentials"
}
)
aws_keys = response.json()
print(f"Access Key: {aws_keys['canarytoken']['access_key_id']}")
print(f"Secret Key: {aws_keys['canarytoken']['secret_access_key']}")
# Plant in .aws/credentials on developer workstationsAll deception alerts are high-fidelity — any interaction is suspicious:
Splunk Alert for Canary Triggers:
index=canary sourcetype="canary:alerts"
| eval severity = "CRITICAL"
| eval confidence = "HIGH — Deception asset triggered, zero false positive expected"
| table _time, canary_name, alert_type, source_ip, service, details
| sendalert create_notable param.rule_title="Deception Alert — Canary Triggered"
param.severity="critical" param.drilldown_search="index=canary source_ip=$source_ip$"SOAR Automated Response:
def canary_triggered(container):
"""Auto-response for deception alerts — high confidence, no approval needed"""
source_ip = container["artifacts"][0]["cef"]["sourceAddress"]
# Immediately isolate the source
phantom.act("quarantine device",
parameters=[{"ip_hostname": source_ip}],
assets=["crowdstrike_prod"],
name="isolate_attacker_host")
# Block at firewall
phantom.act("block ip",
parameters=[{"ip": source_ip, "direction": "both"}],
assets=["palo_alto_prod"],
name="block_attacker_ip")
# Create high-priority incident
phantom.act("create ticket",
parameters=[{
"short_description": f"DECEPTION ALERT: Canary triggered from {source_ip}",
"urgency": "1",
"impact": "1"
}],
assets=["servicenow_prod"])
phantom.set_severity(container, "critical")Regularly update decoys to maintain believability:
| Term | Definition |
|---|---|
| Honeypot | Decoy system mimicking real infrastructure to attract and detect attackers in the network |
| Honeytoken | Fake credential, file, or data record that triggers an alert when accessed or used |
| Canary | Lightweight deception device or token that alerts on any interaction (Thinkst Canary platform) |
| Breadcrumb | Planted artifact (cached credential, bookmark, config file) leading attackers to deception assets |
| High-Fidelity Alert | Detection signal with near-zero false positive rate because no legitimate user should interact with deception assets |
| Decoy Network | Set of interconnected honeypots simulating a realistic network segment to observe attacker TTPs |
DECEPTION ALERT — CRITICAL
━━━━━━━━━━━━━━━━━━━━━━━━━━
Time: 2024-03-15 14:23:07 UTC
Canary: FILESERVER-BK04 (10.0.5.200)
Service: SMB — File share "Finance_Backup" accessed
Source: 192.168.1.105 (WORKSTATION-042, Finance Dept)
User: company\jsmith
File Accessed: Q4_Revenue_2024.xlsx (canary document)
Alert Confidence: HIGH — No legitimate reason to access deception asset
False Positive Likelihood: <1%
Automated Response:
[DONE] WORKSTATION-042 isolated via CrowdStrike
[DONE] 192.168.1.105 blocked at firewall (bidirectional)
[DONE] Incident INC0012567 created (P1 — Critical)
[PENDING] Tier 2 investigation — determine if workstation compromised or insider threat© mukul975, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (scripts, references) in skills/performing-deception-technology-deployment of mukul975/Anthropic-Cybersecurity-Skills.
Open the folder on GitHubat commit 54a7988
Performing Deception Technology Deployment 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 |
|---|---|---|---|---|---|---|
| Performing Deception Technology Deployment this skillmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~2.8k | Automated safety check: Warn | Apache-2.0 | |
| Agent Red Teamingseb1n/awesome-ai-agent-skills | 206 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Councilwarpdotdev/common-skills | 611 | 1 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Cybersecurityohmyjahh/xquads-squads | 277 | — | ~895 | Automated safety check: Pass | MIT | |
| Rational Red Blue Debatedigoal/blog | 8.6k | — | ~2.2k | Automated safety check: Pass | GPL-2.0 | |
| Threat Huntinghypnguyen1209/offensive-claude | 388 | — | ~2.4k | Automated safety check: Pass | MIT |
seb1n/awesome-ai-agent-skills
Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings.
warpdotdev/common-skills
Run a model-diverse subagent council to investigate the same problem from multiple perspectives, compare findings, and produce a final recommendation.
ohmyjahh/xquads-squads
Squad de 15 agentes de seguranca ofensiva e defensiva (Georgia Weidman, Peter Kim, Jim Manico, Chris Sanders, Omar Santos, Marcus Carey) cobrindo pentest, red team, blue team, AppSec, recon e…
digoal/blog
Answer general or cross-domain questions with a non-pleasing rational mode: adversarial red-team and blue-team expert analysis, mutually exclusive conclusions, up to five debate rounds, saved…
hypnguyen1209/offensive-claude
A skill your agent uses when hunting threats or engineering detections — ATT&CK Detection-Strategies, Sigma + correlation with Detection-as-Code CI, Windows endpoint hunting…
google/skills
Expert guidance for deep security incident and entity investigations in Google SecOps.
mukul975/Anthropic-Cybersecurity-Skills
Weighs infrastructure, TTP, malware code and timing evidence with the Diamond Model and competing hypotheses to reach a confidence-rated attribution.
mukul975/Anthropic-Cybersecurity-Skills
Walks through reverse engineering Go-compiled malware in Ghidra: parsing buildinfo and pclntab, recovering stripped function names and extracting dependencies.
mukul975/Anthropic-Cybersecurity-Skills
Guides forensic analysis of Windows LNK shortcut files and Jump Lists with LECmd, JLECmd and manual parsing to show file access and program execution.
mukul975/Anthropic-Cybersecurity-Skills
Hunts Windows malware persistence with Sysinternals Autoruns, covering run keys, services, scheduled tasks and drivers, with baseline comparison.
mukul975/Anthropic-Cybersecurity-Skills
Guides a Windows forensic examination of the NTFS Master File Table to recover deleted-file evidence, build timelines and spot timestomping.
mukul975/Anthropic-Cybersecurity-Skills
Detects DNS tunneling, ICMP exfiltration and HTTP-based covert channels in packet captures and DNS logs when hunting for hidden command-and-control traffic.
Categories
Deploys deception technology including honeypots, honeytokens, and decoy systems to detect attackers who have bypassed perimeter defenses, providing high-fidelity alerts with near-zero false…. Performing Deception Technology Deployment is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Deploys deception technology including honeypots, honeytokens, and decoy systems to detect attackers who have bypassed perimeter defenses, providing high-fidelity alerts with near-zero false positive rates.
Performing Deception Technology Deployment fits situations like: SOC teams need early warning of lateral movement; credential abuse; internal reconnaissance by deploying convincing traps across the network.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill performing-deception-technology-deployment -a claude-code`. Or copy the skill folder (skills/performing-deception-technology-deployment in mukul975/Anthropic-Cybersecurity-Skills) into .claude/skills/performing-deception-technology-deployment in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill performing-deception-technology-deployment -a codex`. Or copy the skill folder (skills/performing-deception-technology-deployment in mukul975/Anthropic-Cybersecurity-Skills) into .agents/skills/performing-deception-technology-deployment 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 mukul975/Anthropic-Cybersecurity-Skills --skill performing-deception-technology-deployment -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/performing-deception-technology-deployment, .gemini/skills/performing-deception-technology-deployment, .github/skills/performing-deception-technology-deployment and .opencode/skills/performing-deception-technology-deployment in your project.
Going by SKILL.md and its folder, Performing Deception Technology Deployment needs Python for the scripts in its folder. Our summary lists: Python 3; Docker; A credential in YOUR_API_TOKEN.
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 flagged 2 warning(s): mentions a credentials file (ssh keys, cloud or package-manager tokens). Read the flagged lines before installing; the check is not a guarantee either way. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Performing Deception Technology Deployment is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 540 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Performing Deception Technology Deployment: Agent Red Teaming (seb1n/awesome-ai-agent-skills, 206 stars), Council (warpdotdev/common-skills, 611 stars), Cybersecurity (ohmyjahh/xquads-squads, 277 stars) and Rational Red Blue Debate (digoal/blog, 8.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mukul975 (a GitHub user) maintains it in mukul975/Anthropic-Cybersecurity-Skills, which has 33,993 GitHub stars. The repository holds 644 skills in this directory. The repository was last updated on August 31, 2026.
Source: mukul975/Anthropic-Cybersecurity-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.