cutagent-b-roll
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content including video transcripts and project media files. This creates a potential surface for indirect prompt injection where instructions embedded in transcripts could attempt to influence the agent's behavior.
- Ingestion points: Processes transcripts, motion data, and project media referenced in the instructions.
- Boundary markers: The instructions do not explicitly define delimiters or markers to separate untrusted transcript content from agent instructions.
- Capability inventory: The skill implies the use of the 'CutAgent CLI' for file modification and timeline editing.
- Sanitization: No explicit sanitization or validation of the input transcript content is mentioned.
- [SAFE]: No credentials, malicious network operations, obfuscation, or persistence mechanisms were found in the skill content. The reference to 'CutAgent CLI' and local SDK declarations appears to be standard configuration for its intended video editing purpose.
Audit Metadata