Test RAG vector stores (Pinecone, Qdrant, Weaviate, Chroma, pgvector, FAISS) for embedding inversion, cross-tenant data leakage, and data poisoning per OWASP LLM08:2025. Use when performing an authorized security assessment of a RAG pipeline's retrieval layer or auditing multi-tenant vector-store isolation.
Install
npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill assessing-vector-and-embedding-weaknessesnpx skills add mukul975/Anthropic-Cybersecurity-Skills --skill assessing-vector-and-embedding-weaknesses -a claude-code -gnpx skills add mukul975/Anthropic-Cybersecurity-Skills --skill assessing-vector-and-embedding-weaknesses -a codex -ggemini skills install https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git --path skills/assessing-vector-and-embedding-weaknessesgh skill install mukul975/Anthropic-Cybersecurity-Skills assessing-vector-and-embedding-weaknessesgit clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills /tmp/mukul975__Anthropic-Cybersecurity-Skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/mukul975__Anthropic-Cybersecurity-Skills/skills/assessing-vector-and-embedding-weaknesses ~/.claude/skills/assessing-vector-and-embedding-weaknesses # Claude Code
cp -R /tmp/mukul975__Anthropic-Cybersecurity-Skills/skills/assessing-vector-and-embedding-weaknesses ~/.agents/skills/assessing-vector-and-embedding-weaknesses # Codex, Cursor, Gemini CLI, Copilot, OpenCode