repurpose-into-a-post
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input data from articles, transcripts, and documents which could contain hidden instructions aimed at overriding agent behavior. \n
- Ingestion points: The skill ingests user-supplied content such as articles, newsletters, transcripts, and video documents for transformation into social media posts. \n
- Boundary markers: The skill lacks explicit boundary markers or instructions to treat the ingested text as data rather than instructions. \n
- Capability inventory: The skill mentions capabilities to schedule posts and send one-time codes via external tools (e.g.,
schedule_post). \n - Sanitization: No sanitization or filtering of the source text is described to prevent instruction leakage.
Audit Metadata