overseerr

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Node.js scripts to perform its operations. These scripts are invoked by the agent to interact with the Overseerr API.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes external data from both user input and the Overseerr API.
  • Ingestion points: Media titles, request IDs, and search queries provided via CLI arguments; search results and request status data returned from the Overseerr API.
  • Boundary markers: The skill does not implement specific delimiters to isolate external content within the agent's context.
  • Capability inventory: The skill's capabilities are limited to performing authenticated network requests (GET and POST) to the user-provided Overseerr URL.
  • Sanitization: Inputs are sanitized using standard mechanisms such as encodeURIComponent for URL paths and URLSearchParams for query strings before being sent to the API.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 04:40 AM
Security Audit — agent-trust-hub — overseerr