bug-triage
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of untrusted bug reports.
- Ingestion points: The agent reads bug report files from production/qa/bugs/*.md and consolidated logs in production/qa/bugs.md (Step 2a).
- Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the processed bug reports.
- Capability inventory: The skill uses Read, Glob, Grep, Write, and Edit tools to process data and generate a triage report (Step 5).
- Sanitization: There is no evidence of sanitization or validation of the content read from bug reports before it is processed or included in the output report.
Audit Metadata