tmdb

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes movie metadata such as titles and overviews from the external TMDb API, which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: Untrusted data is retrieved from api.themoviedb.org within the search, movie, tv, and suggest commands in scripts/tmdb.py.
  • Boundary markers: The skill does not use specific delimiters to wrap external content when returning it to the agent context.
  • Capability inventory: The skill's capabilities are limited to network requests to the TMDb API and writing to local files (watchlist.json, preferences.json). It does not perform arbitrary command execution or access sensitive system files.
  • Sanitization: The script performs basic sanitization by truncating movie overviews to 200 characters.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 05:34 AM
Security Audit — agent-trust-hub — tmdb