cardiology-content-repurposer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): Potential for indirect prompt injection via untrusted source material.
- Ingestion points: The skill is designed to process external content such as YouTube transcripts, PDFs, and newsletters provided by the user as described in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore prompts that might be embedded within the processed medical content.
- Capability inventory: The skill utilizes tool calls (PubMed:search_articles, PubMed:get_article_metadata) and produces structured content across multiple formats.
- Sanitization: No sanitization or validation of the input source material is performed before processing or using it to trigger PubMed searches.
Audit Metadata