jellyfin-cli

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The use of subprocess.run is confined to the test suite (tests/test_jellyfin_cli.py) for the purpose of validating CLI argument handling. It targets the local bundled script and does not execute arbitrary shell commands.
  • [DATA_EXFILTRATION]: The skill transmits an API key to the Jellyfin server URL provided by the user. This is documented, intended behavior for an API client and follows standard security practices by using environment variables for the secret.
  • [PROMPT_INJECTION]: Data retrieved from the Jellyfin server (titles, descriptions) is passed to the agent's context. This constitutes a potential indirect prompt injection surface, though the skill's read-only nature and lack of dangerous capabilities minimize the associated risk.
  • Ingestion points: API responses in scripts/jellyfin-cli.
  • Boundary markers: None.
  • Capability inventory: Read-only API access; no write or execution capabilities.
  • Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 09:20 PM
Security Audit — agent-trust-hub — jellyfin-cli