Skills
Navigate
skills/alivirgo/major-ai-skills/chromadb/Gen Agent Trust Hub

chromadb

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes processes for ingesting and querying external documents for RAG (Retrieval-Augmented Generation), creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: SKILL.md (via the documents parameter in the col.upsert function).
  • Boundary markers: The skill suggests redacting secrets at ingest, but the code snippets lack explicit delimiters or instructions for the agent to disregard commands within ingested data.
  • Capability inventory: SKILL.md and gpt.md (file system access via PersistentClient and network access through embedding providers and HttpClient).
  • Sanitization: No explicit sanitization or filtering of the ingested document content is demonstrated in the provided code examples.
  • [EXTERNAL_DOWNLOADS]: References the chromadb library and official documentation from docs.trychroma.com and cookbook.chromadb.dev.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 10:30 PM