jira-agile-management
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes untrusted JIRA issue data such as summaries and descriptions. Evidence: (1) Ingestion points: JIRA issue fields and backlog lists accessed via the jira-as agile commands. (2) Boundary markers: No delimiters or instructions are provided in the documentation to help the agent distinguish between administrative instructions and data-embedded instructions. (3) Capability inventory: The skill utilizes the Bash tool, providing an attack surface if malicious instructions are ingested. (4) Sanitization: Not verifiable as no implementation logic or scripts were included in the provided files.
- [No Code] (SAFE): No executable code files were found in the analyzed skill; it relies on documentation to guide agent interaction with an external CLI.
Audit Metadata