qe-defect-intelligence
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions.
- Ingestion points: The skill ingests PR changes, Jira defect data, git commit history, and test results for analysis as defined in SKILL.md and evals/qe-defect-intelligence.yaml.
- Boundary markers: No explicit instructions for delimiting or ignoring instructions within the external data are provided in the skill instructions.
- Capability inventory: The skill utilizes the aqe CLI tool to perform defect prediction, pattern analysis, and root cause analysis as shown in the activation and workflow sections of SKILL.md.
- Sanitization: There is no evidence of specific sanitization or filtering logic for the ingested data from external trackers or repositories.
Audit Metadata