cisco-ai-defense
Security Scanner for Agent Skills
Stars: 2,571
Last Updated: Oct 1, 2026
Security
Agent skills for offensive and defensive security: reconnaissance, CTF solving, vulnerability scanning, and skill-package auditing.
9 skills
#NameAuthorDescriptionStarsLast Updated
#2elementalsouls
8 Claude skills · 100+ recon capabilities · 80 secret-regex patterns · 80+ dorks · 9 read-only credential validators · 27 attack-path templates · ~10,000 lines of structured tradecraft. Drop-in SKILL.md files that turn Claude into a god-mode external recon operator for authorized red-team and bug-bounty engagements.
2,718Aug 30, 2026elementalsouls
8 Claude skills · 100+ recon capabilities · 80 secret-regex patterns · 80+ dorks · 9 read-only credential validators · 27 attack-path templates · ~10,000 lines of structured tradecraft. Drop-in SKILL.md files that turn Claude into a god-mode external recon operator for authorized red-team and bug-bounty engagements.
Stars: 2,718
Last Updated: Aug 30, 2026
#3gadievron
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.
3,839Oct 1, 2026Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.
Stars: 3,839
Last Updated: Oct 1, 2026
#4jherrodthomas
100+ installable Claude skills covering Engineering areas such as, ISO 26262 functional safety, ISO/SAE 21434 cybersecurity, ISO 21448 SOTIF, AIAG-VDA quality (APQP/PPAP/FMEA), Automotive SPICE, and continuous improvement tools — every builder paired with a confirmation reviewer.
2,996Oct 1, 2026jherrodthomas
100+ installable Claude skills covering Engineering areas such as, ISO 26262 functional safety, ISO/SAE 21434 cybersecurity, ISO 21448 SOTIF, AIAG-VDA quality (APQP/PPAP/FMEA), Automotive SPICE, and continuous improvement tools — every builder paired with a confirmation reviewer.
Stars: 2,996
Last Updated: Oct 1, 2026
#5ljagiello
Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more
3,382Sep 13, 2026ljagiello
Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more
Stars: 3,382
Last Updated: Sep 13, 2026
#6NVIDIA
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
19,002Sep 30, 2026Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
Stars: 19,002
Last Updated: Sep 30, 2026
#7prompt-security
A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect your SOUL.md (etc') with drift detection, live security recommendations, automated audits, and skill integrity verification. All from one installable suite.
1,110Oct 2, 2026prompt-security
A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect your SOUL.md (etc') with drift detection, live security recommendations, automated audits, and skill integrity verification. All from one installable suite.
Stars: 1,110
Last Updated: Oct 2, 2026
#8SnailSploit
claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.
7,180Sep 19, 2026SnailSploit
claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.
Stars: 7,180
Last Updated: Sep 19, 2026
#9tech-leads-club
The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with absolute confidence.
7,026Sep 20, 2026tech-leads-club
The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with absolute confidence.
Stars: 7,026
Last Updated: Sep 20, 2026
Related tutorials
Gate Risky Installs and Detect Drift with ClawSec for Agent Runtimes
ClawSec adds signed advisory intelligence, guarded installs, and drift detection to OpenClaw, NanoClaw, Hermes, and Picoclaw agent runtimes.
Run Authorized Red Team Work with Claude-Red's 78 Offensive Skills
Install a 78-skill offensive security library that primes Claude with red team methodology for 23 attack surface categories.
claude-osint: 8 Skills That Turn Claude Into an Authorized Recon Analyst
A 2,583-star library of eight SKILL.md files that give Claude external-recon methodology for assets you own or are authorized to assess, with hard boundaries against active exploitation.
raptor: An Autonomous Security Research Framework for Claude Code
gadievron's 3,700-star RAPTOR chains static analysis, binary analysis, LLM-powered vulnerability validation, and patch writing into one workflow — built by a team of veteran security researchers and sandboxed by default.
ctf-skills: Nine Category Skills for Capture the Flag
ljagiello's 3,162-star ctf-skills packages web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and malware analysis into nine category skills your coding agent loads mid-competition, with a solve-challenge orchestrator on top.
automotive-skills-suite: ISO 26262/21434 Deliverables as Paired Builder + Reviewer Skills
A 2.4k-star Claude-focused suite with 152 installable skills — 76 builders paired with 76 confirmation reviewers — that produce the xlsx artifacts required across automotive safety, cybersecurity, quality, and diagnostics.
skill-scanner: Scan Agent Skills for Prompt Injection and Malicious Patterns
Cisco AI Defense's 2.5k-star Apache-2.0 scanner — YAML+YARA signatures, LLM-as-a-judge, and behavioral dataflow analysis detect prompt injection, data exfiltration, and malicious code in skill packages, with SARIF output for CI.
agent-skills: A Hardened, Validated Skill Registry for Pro Coding Agents
A managed skill registry with static analysis in CI/CD, lockfile integrity, Snyk Agent Scan before publishing, and a defensive CLI — built to address the 13.4% critical-issue rate the README cites in open marketplaces.
Scan Agent Skills for Security Risks with NVIDIA SkillSpector
Install SkillSpector and scan agent skills for vulnerabilities, malicious patterns, and security risks before you install them. Learn static scanning, risk scoring, LLM analysis, and CI integration.