triage-findings-list
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple report files (
*-report.md) located in the.scratchpaddirectory to generate a consolidated change list. - Ingestion points: The skill reads every
*-report.mdin.scratchpad/<slug>/to identify findings and source tags. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when reading the contents of these reports.
- Capability inventory: The skill uses the
execute-plan-looptool to apply approved changes to the codebase based on the triaged list, which involves file modifications or command execution. - Sanitization: There is no mention of sanitizing or validating the input data from the reports before the agent interpolates it into the
change-list.mdand subsequent execution plan.
Audit Metadata