repurpose-video
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external source files (transcripts and research notes) which constitutes a vulnerability surface for indirect prompt injection. \n
- Ingestion points: SKILL.md loads data from research.md, plan.md, and transcript.md in the ./youtube/episode/ directory. \n
- Boundary markers: The skill does not implement delimiters or specific instructions to isolate untrusted content from the content brief extraction process. \n
- Capability inventory: The skill performs local file reads, creates a repurposed.md file, and triggers the creator-stack:write skill for multi-platform content generation. \n
- Sanitization: No sanitization or filtering logic is present to validate the integrity of the source material before processing.
Audit Metadata