mutation-adequacy
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external mutation reports generated by the analysis of source code and incorporates this content into review reports and automated follow-up tasks.
- Ingestion points: The skill reads the 'data' carrier (specifically the 'report' and 'next_actions' fields) returned by the 'exarchos:exarchos_orchestrate' tool.
- Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are defined when interpolating the mutation report data into the review update output.
- Capability inventory: The skill has the capability to modify the project's review state via the 'exarchos:exarchos_workflow' update action.
- Sanitization: The skill does not implement sanitization or validation of the file paths, line numbers, or mutant descriptions extracted from the external report before they are recorded in the workflow state.
Audit Metadata