triage-issue
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user-provided bug descriptions and uses them to guide its logic. The instructions explicitly minimize user interaction and skip review before creating GitHub issues, which reduces the opportunity to detect malicious instructions embedded in a user's problem report.
- Ingestion points: Step 1 (Capture the problem) in SKILL.md.
- Boundary markers: None present to delimit user input from instructions.
- Capability inventory: Full codebase exploration (Agent tool), git log, and gh issue create in SKILL.md.
- Sanitization: None identified.
- [COMMAND_EXECUTION]: The skill performs shell commands using git and the GitHub CLI (gh). While these are intended for the skill's functionality, they represent a capability that could be targeted by injection attacks.
Audit Metadata