Assessing Vector and Embedding Weaknesses
Test vector stores for embedding inversion, cross-tenant leakage, and poisoning.
Install
npx skills add adriannoes/awesome-agentic-ai --skill assessing-vector-and-embedding-weaknessesgit clone --depth 1 https://github.com/adriannoes/awesome-agentic-ai.git /tmp/awesome-agentic-ai
mkdir -p ~/.claude/skills
cp -r /tmp/awesome-agentic-ai/cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/assessing-vector-and-embedding-weaknesses ~/.claude/skills/assessing-vector-and-embedding-weaknessesPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Assessing Vector and Embedding Weaknesses > **Authorized use only:** These tests interact with vector stores and embedding models in RAG systems you own or are authorized to assess. Embedding inversion and cross-tenant probing against systems you do not control may expose third-party data and is prohibited without authorization. ## Overview Retrieval-Augmented Generation (RAG) systems convert documents into embedding vectors stored in a vector database (Pinecone, Qdrant, Weaviate, Chroma, pgvector, FAISS) and retrieve the nearest vectors to ground LLM responses. OWASP **LLM08:2025 Vector and Embedding Weaknesses** covers the security risks unique to this layer: - **Embedding inversion** — embeddings are not one-way. A trained inversion model (or a black-box reconstruction attack) can recover substantial portions of the original text from its vector, leaking source documents (maps to MITRE ATLAS **AML.T0024.001 Invert ML Model**). - **Membership inference** — querying whether a specific record contributed to the corpus (AML.T0024.000). - **Cross-tenant / multi-tenant leakage** — when one namespace/collection is shared or filter isolation is missing, a tenant retrieves another tenant's chunks. - **Knowledge-base poisoning** — an attacker who can write to the corpus inserts crafted chunks that dominate retrieval (high cosine similarity to expected queries) and carry indirect prompt-injection payloads.
Details
- Skill name
assessing-vector-and-embedding-weaknesses- Repository
- adriannoes/awesome-agentic-ai
- Path
cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/assessing-vector-and-embedding-weaknesses/SKILL.md- License
- MIT
- Repo updated
- 2 November 2026
FAQ
What does the Assessing Vector and Embedding Weaknesses skill do?
Test vector stores for embedding inversion, cross-tenant leakage, and poisoning.
How do I install the Assessing Vector and Embedding Weaknesses skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add adriannoes/awesome-agentic-ai --skill assessing-vector-and-embedding-weaknesses. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Assessing Vector and Embedding Weaknesses popular?
It lives in adriannoes/awesome-agentic-ai, which has 100 GitHub stars and 27 forks, and is included in 2 curated skill lists.
Related skills
Browserstack
100adriannoes/awesome-agentic-ai
Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari", "test on firefox", or "browser compatibility".
Coverage
100adriannoes/awesome-agentic-ai
Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".
Fix
100adriannoes/awesome-agentic-ai
Fix failing or flaky Playwright tests. Use when user says "fix test", "flaky test", "test failing", "debug test", "test broken", "test passes sometimes", or "intermittent failure".
Auditing MCP Servers for Tool Poisoning
100adriannoes/awesome-agentic-ai
Scan Model Context Protocol servers and tool metadata for poisoning, SSRF, and unauthenticated exposure.
Analyzing Powershell Empire Artifacts
100adriannoes/awesome-agentic-ai
Detect PowerShell Empire framework artifacts in Windows event logs by identifying Base64 encoded launcher patterns, default user agents, staging URL structures, stager IOCs, and known Empire module signatures in Script Block Logging events.
Autoresearch
100adriannoes/awesome-agentic-ai
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.