ketchup
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize data from external and potentially untrusted sources.
- Ingestion points: As described in the 'Gather what changed' section of SKILL.md, the agent collects chat history, pull request (PR) statuses, CI/CD reports, and messages from other agents or users.
- Boundary markers: There are no instructions provided to use delimiters or specific system instructions to disregard or escape instructions embedded within the data being summarized.
- Capability inventory: The skill allows the agent to read local skill files, use browser tools for screenshots (
screencapture), and open generated visualization files (open <file>). - Sanitization: The instructions do not include steps to sanitize, validate, or escape the content retrieved from external sources before it is processed or presented to the user.
Audit Metadata