hunt-llm-ai

hunt-llm-ai is a Penetration testing & red team skill for AI agents, published by H-mmer in the pentest-agents repository on GitHub. Skillspace rates hunt-llm-ai F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.

Hunting skill for LLM and Agentic AI vulnerabilities — direct + indirect prompt injection, ASCII smuggling data exfil, agentic tool-use abuse, system prompt leakage, vector DB cross-tenant, model server RCE, insecure output handling. Built from public bug bounty reports across HackerOne, Huntr, Project Zero, GitHub Security Advisories, plus 2024-2026 meta verified against NVD — Microsoft 365 Copilot ASCII Smuggling (Johann Rehberger Aug 2024 disclosure), CVE-2025-46059 LangChain GmailToolkit indirect prompt injection (CVSS 9.8), CVE-2025-68613 LangChain PythonREPLTool semantic RCE (CVSS 9.8), CVE-2024-46946 LangChain LLMSymbolicMathChain sympy.sympify, CVE-2025-27520 + CVE-2025-32375 + CVE-2024-2912 BentoML pickle, Ollama RCE family (CVE-2024-37032, CVE-2024-39722, CVE-2024-45436, CVE-2025-44779), CVE-2025-64496 Open WebUI Direct Connections SSE code injection (GHSA-cm35-v4vp-5xvx), CVE-2024-1483/1560/1594 MLflow path traversal. Covers OWASP LLM Top 10 v2025 (LLM01-LLM10) and OWASP…

Grade
F
Quality
45 / 100
Safety
Risky
GitHub stars
930

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since.

View source on GitHubH-mmer/pentest-agents

Our review

Architecture
68 / 100
Maturity
Basic: a single SKILL.md
Security scan
High-risk patterns
License
Not declared. Check the repository before reusing it.

What the scanner flagged

  • prompt-injection: ignore-previous
  • exfiltration language
  • accesses sensitive system files
  • executes shell/subprocess
  • dynamic code execution (eval/exec)
  • mentions secrets in text

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Penetration testing & red team

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.