ketchup-video
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from chat history, subagent reports, and code diffs to generate summaries and videos, creating a potential surface for indirect prompt injection.\n
- Ingestion points:
references/ketchup.md(chat messages, subagent reports),SKILL.md(screenshots, recordings, diffs, and work data).\n - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for the ingested content.\n
- Capability inventory: The skill is authorized to write and render video files (mp4) using available tools.\n
- Sanitization: No explicit sanitization or filtering of the processed content is described.\n- [EXTERNAL_DOWNLOADS]: The skill's
UPSTREAM.mdfile references and tracks its source code from the officialcursor/pluginsrepository on GitHub, which is a well-known service.
Audit Metadata