film-editor
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process clip transcripts to identify audio-leading (J-cuts) and picture-leading (L-cuts) transition points. This constitutes an ingestion point for potentially untrusted data that could influence agent behavior. 1. Ingestion points: Accesses clip-level data via semanticProfile.transcript and silenceRegions in SKILL.md. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the transcripts are provided. 3. Capability inventory: The skill utilizes media manipulation tools including specialist_consult, detachAudio, sliceClip, and splitClip. 4. Sanitization: There is no evidence of transcript content sanitization, validation, or escaping prior to use in the editing workflow.
Audit Metadata