grok-video-edit
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of command-line tools such as 'uv run' and 'ffmpeg' to process video files, including trimming, re-encoding, and merging segments.
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates user-provided text prompts into shell command arguments for the 'grok-edit' utility, which represents a potential attack surface. * Ingestion points: User-provided editing prompts described in SKILL.md. * Boundary markers: Examples show the use of double quotes for the prompt argument, but there are no specific instructions for escaping or sanitizing shell metacharacters. * Capability inventory: The workflow utilizes 'uv run' and 'ffmpeg' to perform system-level operations. * Sanitization: There is no mention of sanitizing or validating the user-provided prompt string before it is used in a command-line context.
Audit Metadata