grok-video-edit
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external video files and user-supplied text prompts which are interpreted by a generative AI model (Grok) to reimagine footage.
- Ingestion points: Video files (e.g.,
source.mp4,segment.mp4) and user prompts via the--promptargument inSKILL.md. - Boundary markers: None specified in the instructions to delimit user content from system instructions.
- Capability inventory: Shell command execution via
ffmpegand thevideo-agentCLI toolkit documented inSKILL.md. - Sanitization: No explicit sanitization or validation of input content is described in the workflow.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands to perform video manipulation tasks.
- Evidence: Multiple instances of
ffmpegusage for muxing, concatenation, and filtering, as well asuv run video-agentfor trimming and editing inSKILL.md. - [EXTERNAL_DOWNLOADS]: The skill documentation references and encourages the use of an external toolkit hosted on GitHub.
- Evidence: Refers to
https://github.com/agamm/video-agentinSKILL.mdandUPSTREAM.mdas the required environment for the provided scripts.
Audit Metadata