create-captions
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill includes a clear security notice advising the agent to treat scraped content and transcripts as untrusted data, effectively mitigating potential indirect prompt injection attacks from processed media.
- [COMMAND_EXECUTION]: The skill instructions involve executing local scripts and tools (Node.js, Python, ffmpeg) using shell commands for video processing. These operations use standard placeholders for file paths and names and do not involve privilege escalation or persistence mechanisms.
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npx remotion, a well-known technology service for video programmatics. This usage follows standard developer patterns and is consistent with the skill's stated purpose.
Audit Metadata