Skills for Real Engineers. Straight from my .agents directory.
39 skills
hunt-llm-ai
Agent skill from
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 history/secrets), markdown-image zero-click exfil, system-prompt extraction, IDOR-via-AI (cross-tenant data). Targets: chatbots, RAG, summarizers, agentic copilots, MCP tools. Detection: any LLM-backed endpoint, doc upload triggering AI processing, autonomous agent with tools. Validate: OOB/Collaborator callback for exfil, verbatim-reproducible system-prompt leak (run twice), verifiable cross-tenant leak or RCE. Confabulation is NOT a finding. Use when hunting AI features, chatbots, RAG, agentic s
How to install hunt-llm-ai
install hunt-llm-ai
# install the Claude-BugHunter pack with the skills CLI
npx skills add elementalsouls/Claude-BugHunter# or add only this skill to Claude Code: copy the folder
skills/hunt-llm-ai/
# into
~/.claude/skills/hunt-llm-ai/ (all projects)
.claude/skills/hunt-llm-ai/ (one project)
1## 11. LLM / AI FEATURES23LLM bugs are only worth reporting when they cross a trust boundary you can **prove** — an OOB callback, a verbatim-reproducible secret, a cross-tenant record, or code execution. A model "saying something bad once" is confabulation, not a vulnerability. Read the False-Positive Gate before claiming anything.45> **Naming note (was wrong in v1):** the model-level list is **OWASP Top 10 for LLM Applications 2025** (LLM01 Prompt Injection, LLM07 System Prompt Leakage, LLM08 Vector/Embedding Weaknesses). The agent-level list is **OWASP Top 10 for Agentic Applications (2026)** from the **Agentic Security Initiative (ASI)**, codes ASI01–ASI10. Do not write "OWASP ASI 2026" as if it were one document — cite the correct list per finding.67---89## False-Positive Gate (Read First)1011LLMs are non-deterministic. The single biggest source of bogus LLM reports is **confabulation** — the model inventing a plausible "system prompt" or "other user's data" that is not real. Apply every check below before writing a word.12131. **Run-twice rule (verbatim reproducibility).** Send the identical extraction prompt in two fresh sessions (clear cookies/conversation). A real system-prompt leak reproduces **token-for-token**. If the two outputs differ in wording, structure, or detail, it is confabulation — discard it.14…
Excerpt shown under the repository's MIT license.
More skills in Claude-BugHunter
Keep exploring
Similar skill repositories
An agentic skills framework & software development methodology that works.
15 skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
CC1 skill
Public repository for Agent Skills
20 skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
CCCU6 skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
CCCXCUGH6 skills