podcast-research
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified in the skill. The capabilities are limited to read-only research via standard search providers.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a standard attack surface for indirect prompt injection as it processes external content from search results and video captions.
- Ingestion points: Data is ingested from
youtube_web_v2_video_captions,exa_search, andtavily_search(SKILL.md). - Boundary markers: The workflow instructs the agent to cite sources and separate observations from interpretations, creating a logical boundary for external data (SKILL.md).
- Capability inventory: The skill is restricted to read-only tools and explicitly forbids taking actions on external platforms.
- Sanitization: No specific sanitization methods for external data are described.
Audit Metadata