Hunt LLM AI
Hunt LLM AI is an agent skill (a SKILL.md file) from elementalsouls/Claude-BugHunter. 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). It works with Claude Code, Codex and OpenCode and has 6,913 GitHub stars across a repository of 4 listed skills.
github.com/elementalsouls/Claude-BugHunter/skills/hunt-llm-ai (opens in a new tab)
Data as of from the GitHub API; description from the skill's SKILL.md. Report an error
Add this skill
Claude
This repository is a Claude Code plugin marketplace. In Claude Code:
/plugin marketplace add elementalsouls/Claude-BugHunter
/plugin install claude-bughunter@elementalsoulsIn the Claude apps, zip the hunt-llm-ai folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).
ChatGPT / Codex
Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:
git clone --depth 1 https://github.com/elementalsouls/Claude-BugHunter.git
cp -r Claude-BugHunter/skills/hunt-llm-ai .agents/skills/hunt-llm-ai # repo; ~/.agents/skills for all projectsStandalone skills also load in the ChatGPT desktop app.
Cursor
Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:
git clone --depth 1 https://github.com/elementalsouls/Claude-BugHunter.git
cp -r Claude-BugHunter/skills/hunt-llm-ai .cursor/skills/hunt-llm-ai # project; ~/.cursor/skills for all projectsSource (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), code.claude.com/docs/en/plugin-marketplaces (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)
What this skill does
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…
When it triggers
- Use when hunting AI features, chatbots, RAG, agentic systems, MCP.
More skills in elementalsouls/Claude-BugHunter
4 skills are listed from this repository.
Similar skills
More security skills
Broken Authentication
zebbern/claude-code-guide
This skill should be used when the user asks to "test for broken authentication vulnerabilities", "assess session management security", "perform credential stuffing tests", "evaluate password…
Maintained · last commit Nov 14, 2026
SecurityPythonOpenapi To MCP
mcp-use/mcp-use
Build and deploy an MCP server from an OpenAPI / Swagger spec using the mcp-use TypeScript SDK.
Active · last commit Nov 11, 2026
OfficialSecurityTypeScriptAudit Context Building
trailofbits/skills
Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere.
Maintained · last commit Nov 12, 2026
OfficialSecurityPythonAn
BuilderIO/skills
Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and current screen state.
Maintained · last commit Nov 15, 2026
OfficialSecurityJavaScriptMirrord DB Branching
metalbear-co/mirrord
Helps users configure mirrord.json for database branching, enabling isolated database copies for safe development and testing.
Active · last commit Nov 15, 2026
OfficialSecurityRustUnlazy
Leonxlnx/unlazy
Enforces completion discipline for substantial autonomous work by writing acceptance gates before execution, decomposing work with the Depth Tree, running approved checks, and re-verifying evidence…
Maintained · last commit Sep 3, 2026
SecurityJavaScript
How do I install the Hunt LLM AI skill?
In Claude Code, run /plugin marketplace add elementalsouls/Claude-BugHunter and then /plugin install claude-bughunter@elementalsouls. For Codex or Cursor, copy the hunt-llm-ai folder into .agents/skills/ or .cursor/skills/.
Is the Hunt LLM AI skill free?
Yes. The repository is open source under the MIT license.
Is Hunt LLM AI maintained?
The repository's most recent commit was on Nov 15, 2026. Its latest release is v2.1. appsgit only lists skills from repositories with a commit in the last six months.