test-flakiness
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from NUnit XML test results and CI artifact manifests.
- Ingestion points: Test results and manifests provided via results-path or discovered in production/qa/test-results/.
- Boundary markers: No explicit delimiters are defined for parsing the external XML content.
- Capability inventory: The skill uses Read, Glob, Grep, and Write tools to analyze data and update documentation in production/qa/.
- Sanitization: No explicit sanitization or validation of the XML content is described.
Audit Metadata