rhdh-jira-refine
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or high-risk behaviors were found. The skill performs legitimate Jira project management tasks using authenticated command-line tools.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from Jira issues which could contain malicious instructions. Ingestion points: Issue descriptions and comments are read via acli in workflows/refine-issues.md. Boundary markers: No specific delimiters are defined to isolate external data. Capability inventory: The skill can read and update Jira work items via the acli CLI. Sanitization: The risk is mitigated by requiring explicit user confirmation for all changes and using an internal mutation gate for all write operations.
Audit Metadata