cutagent-voiceover
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to process and act upon untrusted user scripts and audio files.\n
- Ingestion points: Processes user-supplied scripts and recorded audio files as specified in SKILL.md.\n
- Boundary markers: The instructions do not specify any delimiters or safety prompts to prevent the agent from obeying instructions embedded within user scripts.\n
- Capability inventory: Performs file selection and timeline editing via the CutAgent SDK and CLI.\n
- Sanitization: No content sanitization or validation of the input script is required by the workflow.
Audit Metadata