hunt-llm-ai
97 / 100 · Low risk
Fine to try. Some of what it can do is expected: a security skill usually runs scanners and checks websites.
Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model reads, ASCII smuggling (Unicode Tags block U+E0000-U+E007F, invisible to humans, decoded by the model), tool-use exfiltration (model has fetch/browse tool, attacker injects OOB URL, model exfils chat h…
What this skill can do
Runs commands on your computer
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'hunt-llm-ai' ] || [ -L ~/.agents/skills/'hunt-llm-ai' ]; then echo 'A skill folder named hunt-llm-ai already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/elementalsouls/Claude-BugHunter' "$d" && git -C "$d" checkout --quiet '8ac4242ee0a108e65ac1343b56cce6c50ba456ef' -- 'skills/hunt-llm-ai' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/hunt-llm-ai' ~/.agents/skills/'hunt-llm-ai' && 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/'hunt-llm-ai' ~/.claude/skills/'hunt-llm-ai' (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/elementalsouls/Claude-BugHunter/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-14 | 8ac4242 | 97 |
| 2026-11-10 | d5dcc53 | 97 |
| 2026-11-08 | 42a3ab1 | 97 |
| 2026-11-06 | 3e71af0 | 97 |