write-script
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content such as video transcripts and reference data, which could be used to deliver malicious instructions.
- Ingestion points: External transcripts from Reels, TikToks, and YouTube Shorts are processed in
SKILL.md. - Boundary markers: No specific delimiters or security instructions are provided to the agent to isolate external data from its primary instructions.
- Capability inventory: The skill is capable of invoking tools like
edit-videoandfind-ideasand writes to the local filesystem (e.g.,analysis/reel-brief.md). - Sanitization: The skill lacks technical sanitization or validation logic for the external transcripts it processes.
Audit Metadata