pstack-ketchup-video
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to render a video file from slides, which necessitates the invocation of system-level media processing tools (such as ffmpeg). This capability is used to transform image data and metadata into a final mp4 output outside of the repository boundary.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local workspace, including recordings, diffs, and screenshots, which serves as an ingestion point for potentially malicious instructions hidden within those artifacts.\n
- Ingestion points: The agent reads diffs, screenshots, and recordings produced by previous workspace tasks (SKILL.md).\n
- Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard or sanitize instructions that may be embedded within the ingested data.\n
- Capability inventory: The skill allows file writing outside the repository and command execution for the purpose of video rendering.\n
- Sanitization: The instructions do not specify any sanitization or validation logic for data extracted from workspace files before inclusion in the video slides.
Audit Metadata