cutagent-rendering
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external content which may contain hidden instructions.
- Ingestion points: Reading CutAgent SDK or public CLI reference documentation and probing rendered video/audio files (SKILL.md).
- Boundary markers: No specific delimiters or safety instructions are provided to separate external data from instructions.
- Capability inventory: The skill manages local render jobs via CLI/SDK, probes media files, and writes to the local filesystem (SKILL.md).
- Sanitization: No explicit sanitization or validation of the external documentation or file metadata is mentioned.
Audit Metadata