hunt-rag-vector

SKILLFlujo de trabajocomunidad
v0.0.0elementalsoulsMITActualizado hace 5 dFuente →

Hunt vector-store / embedding-layer weaknesses in RAG pipelines (OWASP LLM08 Vector and Embedding Weaknesses) — persistent corpus poisoning that survives across sessions and users (distinct from one-shot indirect prompt injection, which is owned by hunt-llm-ai), cross-tenant vector-database IDOR (un

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
4kEstrellas del repo
1Clientes
1Formatos
hace 5 dÚltima actualización
Skill
Autorelementalsouls
Versión0.0.0
LicenciaMIT
CategoríaFlujo de trabajo
Formatosskill.md
PromptAbrir (ver la pestaña Prompt)
Compatibilidad
Claude✓ Compatible
Cursor
Copilot
ChatGPT
Gemini
Acerca de

Hunt vector-store / embedding-layer weaknesses in RAG pipelines (OWASP LLM08 Vector and Embedding Weaknesses) — persistent corpus poisoning that survives across sessions and users (distinct from one-shot indirect prompt injection, which is owned by hunt-llm-ai), cross-tenant vector-database IDOR (unauthenticated or unscoped queries against Pinecone/Weaviate/Chroma/Milvus/Qdrant/pgvector), source-t

Palabras clave
skillclaude