ketchup-video
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to render a video file (MP4) from generated slides. This process involves executing rendering software or media libraries to create and save a new file to the system.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources including screenshots, recordings, and code diffs to construct slides.
- Ingestion points: Project screenshots, recordings, and diff data found within the repository (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the source visuals or data.
- Capability inventory: The agent possesses file system write access and video rendering capabilities.
- Sanitization: There are no instructions for sanitizing or filtering the content extracted from the visual or textual project data before it is used in the rendering process.
Audit Metadata