triage-issue
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill processes user-provided bug reports. 1. Ingestion points: Error messages and bug reports provided by the user (SKILL.md, Step 1). 2. Boundary markers: The skill does not currently use explicit delimiters to wrap untrusted input. 3. Capability inventory: The skill utilizes Jira tools to add comments and create issues. 4. Sanitization: The workflow mitigates risks by extracting specific error signatures and requiring a human user to review and approve all proposed Jira actions.
Audit Metadata