podcast-research
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests and processes untrusted data from external sources, including YouTube video captions and web search results.
- Ingestion points: External data enters the agent's context through the output of the
youtube_web_v2_video_captions,exa_search, andtavily_searchtools as described in SKILL.md. - Boundary markers: The instructions do not specify the use of boundary markers (e.g., XML tags or delimiters) to separate untrusted content from system instructions, nor do they include warnings to ignore instructions found within the data.
- Capability inventory: The skill uses tools for searching and retrieving external content. It does not exhibit capabilities for writing files, spawning subprocesses, or performing sensitive network operations beyond the intended search functions.
- Sanitization: There are no explicit instructions for the agent to sanitize, escape, or filter content retrieved from external sources before processing it.
Audit Metadata