edit-video
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
ffprobeutility to inspect media stream data and resolution. It also invokes a local Node.js script located atscripts/transcribe-elevenlabs.mjsto perform audio transcription. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources such as project briefs and transcripts, which could contain embedded malicious instructions.
- Ingestion points:
DESIGN.md, project briefs, and transcription data from ElevenLabs. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill instructions.
- Capability inventory: Execution of shell commands (
ffprobe), execution of internal scripts vianode, and extensive file system read/write access for project management. - Sanitization: There is no evidence of sanitization or validation for the content of processed files.
Audit Metadata