chatcut-editing-guide
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions were analyzed and found to be consistent with the described video editing purpose. There are no attempts to exfiltrate data, bypass safety filters, or execute unauthorized commands.
- [NO_CODE]: The skill consists purely of markdown instructions and does not include any scripts, binaries, or configuration files that could hide malicious logic.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define a standard surface for processing external project data, which is inherent to the video editing task.
- Ingestion points: The skill reads project states and video transcriptions during the editing workflow.
- Boundary markers: No specific delimiters or safety instructions for ignoring embedded content in project data are present.
- Capability inventory: The skill utilizes capabilities for reading project state, modifying timelines, and rendering video frames.
- Sanitization: No explicit sanitization or validation of the project data or transcription content is mentioned.
Audit Metadata