test-reliability
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, creating a surface where malicious content in logs could influence agent behavior or reporting.
- Ingestion points: The skill reads CI execution records, rerun logs, triage tables, and historical determination files stored in the
.qa/directory. - Boundary markers: The instructions do not define explicit delimiters or boundary markers to help the agent distinguish between the data content of the logs and its own instructions.
- Capability inventory: The skill generates reliability reports in Markdown format and provides instructions for the
qa-memoryworkflow to update persistent project metadata in the.qa/directory. - Sanitization: There is no mention of sanitization, escaping, or validation of the ingested log content before it is processed by the agent.
Audit Metadata