llm-security
llm-security is an Agent security & guardrails skill for AI agents, published by hardw00t in the ai-security-arsenal repository on GitHub. Skillspace rates llm-security C (73/100) and it passed the safety scan; the rating is based on static analysis only.
LLM and AI application security testing skill for prompt injection (direct, indirect, multimodal), system-prompt extraction, RAG poisoning, memory poisoning, MCP server injection, skill-file injection, agentic tool misuse, computer-use UI injection, and excessive agency. Authorization required — this skill tests AI systems you are explicitly permitted to assess. Triggers on requests to test LLM / AI-agent / RAG / MCP / computer-use security, perform prompt injection, extract system prompts, poison RAG or memory, audit agent tool use, or evaluate AI guardrails.
- Grade
- C
- Quality
- 73 / 100
- Safety
- Passed
- GitHub stars
- 89
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 97 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 1 other repositories, in 0 collections
Not checked 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
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.