youdotcom-api

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of external web content through the You.com APIs, which introduces a potential surface for Indirect Prompt Injection attacks.\n
  • Ingestion points: Data returned from the Research, Search, and Contents APIs as defined in search.output.schema.json, contents.output.schema.json, and research.output.schema.json.\n
  • Boundary markers: SKILL.md includes a clear 'Security' section warning users to treat all API responses as untrusted data and advising against executing code from results.\n
  • Capability inventory: The skill is intended for data retrieval and integration; it does not implement direct shell execution or unsafe eval of the retrieved content.\n
  • Sanitization: Documentation explicitly recommends sanitizing HTML responses before rendering, although no specific sanitization code is provided in the integration examples.\n- [EXTERNAL_DOWNLOADS]: The skill documentation suggests installing standard, well-known Python packages (requests, httpx) to facilitate HTTP communication with the You.com REST endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 03:06 AM