youtube-search-api-skill
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external content from YouTube search results, which could potentially contain adversarial instructions designed to influence the agent's behavior.
- Ingestion points: Untrusted data (video titles, descriptions, and channel names) is fetched in
scripts/youtube_search_api.pyvia the BrowserAct API response and printed to the agent's context. - Boundary markers: The skill does not use specific delimiters or include instructions for the agent to ignore potential commands embedded within the search results.
- Capability inventory: The skill's potential impact is mitigated by its limited capabilities; the scripts do not perform local file writes, execute shell commands, or interact with non-vendor network endpoints.
- Sanitization: The script outputs the raw metadata from YouTube without filtering or sanitizing the content for potential injection strings.
Audit Metadata