qa-flaky-detector
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data sources, which could contain malicious instructions designed to influence the AI's analysis or reporting behavior.
- Ingestion points: The skill parses JUnit XML, Allure JSON reports, and CI job logs from various systems (GitHub Actions, GitLab CI, etc.), and scans test source code (SKILL.md, references/ci-analysis.md).
- Boundary markers: There are no explicit delimiters or boundary markers specified to isolate external data from the agent's internal prompt instructions.
- Capability inventory: The skill is limited to generating Markdown reports and suggesting code fixes; it cannot autonomously execute scripts or modify the codebase without user confirmation.
- Sanitization: The analysis process does not mention sanitization of test names, failure messages, or log content before processing.
Audit Metadata