triage
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from external sources.
- Ingestion points: The skill reads external pull request diffs and markdown issue files located in the
.scratch/directory. - Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when parsing untrusted request bodies or PR diffs.
- Capability inventory: The skill instructions permit file modifications (updating status and appending notes) and command execution (verifying PRs by running tests or commands).
- Sanitization: The instructions do not specify any sanitization or validation of the untrusted content before processing or execution.
Audit Metadata