video-finishing
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a standard workflow for video media processing and normalization within a project workspace. No signs of obfuscation, privilege escalation, or persistence were found.\n- [COMMAND_EXECUTION]: The instructions call for the execution of a local script
scripts/video_finish.pyto handle processing. This is part of the skill's primary function and targets local project files.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads configuration and instructions from an external file to drive the finishing workflow.\n - Ingestion points:
../../references/VIDEO_FINISHING.md(referenced inSKILL.md)\n - Boundary markers: Absent\n
- Capability inventory: Writing to
05_post/video_finish.jsonland executingscripts/video_finish.py(referenced inSKILL.md)\n - Sanitization: Absent
Audit Metadata