google-gemini-file-search
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a technical guide and toolkit for integrating Google Gemini File Search. It includes configuration examples and a utility script (
scripts/create-store.ts) for managing document stores.- [INDIRECT_PROMPT_INJECTION]: As a RAG (Retrieval-Augmented Generation) toolkit, the skill creates an attack surface for indirect prompt injection if the ingested documents contain malicious instructions. Evidence: (1) Ingestion points: Document uploads viauploadToFileSearchStore. (2) Boundary markers: Absent from the provided prompting templates. (3) Capability inventory: Network access to Google APIs via SDK and file system reads. (4) Sanitization: Not explicitly implemented in documentation examples. This is a standard risk for the described technology.- [EXTERNAL_DOWNLOADS]: The skill references the installation of@google/genai, which is the official SDK from a well-known service (Google). Documentation is neutral and follows security standards.- [CREDENTIALS_SAFE]: The skill correctly uses environment variables (GOOGLE_API_KEY) for secret management, preventing credential exposure in code or logs.
Audit Metadata