podcast-blog-post-creator
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external podcast transcripts as the primary data source.
- Ingestion points: The workflow in
SKILL.mdinstructs the agent to read through polished transcripts to identify key insights and quotes. - Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore embedded instructions within the transcript data.
- Capability inventory: The skill contains no scripts, code execution commands, network transmission capabilities, or file system write operations.
- Sanitization: No sanitization or filtering is performed on the ingested transcript content.
- [EXTERNAL_DOWNLOADS]: The skill encourages identifying research-backed claims and linking to peer-reviewed sources from well-known services like the NIH/PubMed Central (
pmc.ncbi.nlm.nih.gov).
Audit Metadata