qe-bug-reporting-excellence
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from user-submitted bug reports, which could contain instructions intended to manipulate the triage or analysis process.
- Ingestion points: Processed data fields such as
bugDescriptionanduserSubmittedBugdefined in the Agent Integration section ofSKILL.md. - Boundary markers: The orchestration examples lack explicit delimiters or instructions to ignore potential commands embedded within bug report text.
- Capability inventory: The skill demonstrates interaction with internal agents such as
qe-quality-analyzerandqe-production-intelligencefor triage, duplicate detection, and root cause analysis. - Sanitization: There is no evidence of input filtering or sanitization logic to handle adversarial content within the bug reports.
Audit Metadata