agent-red-teaming
100 / 100 · Low risk
Fine to try.
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. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'agent-red-teaming' ] || [ -L ~/.agents/skills/'agent-red-teaming' ]; then echo 'A skill folder named agent-red-teaming already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/seb1n/awesome-ai-agent-skills' "$d" && git -C "$d" checkout --quiet '75865a5d037a4cdaa7f409a4ec14ab9b0292920b' -- 'agent-security/agent-red-teaming' && mkdir -p ~/.agents/skills && cp -R "$d"/'agent-security/agent-red-teaming' ~/.agents/skills/'agent-red-teaming' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'agent-red-teaming' ~/.claude/skills/'agent-red-teaming' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/seb1n/awesome-ai-agent-skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | 75865a5 | 100 |