jira
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Jira (issues and comments) and local files which could contain instructions intended to influence the agent's behavior. \n
- Ingestion points:
scripts/jira.pyfetches issue data, comments, and project metadata via the Jira API; it also reads local markdown files via theparse_issue_filefunction. \n - Boundary markers: The script formats Jira data into markdown or JSON for the agent but does not include explicit 'ignore instructions' delimiters for the processed content. \n
- Capability inventory:
scripts/jira.pyhas the ability to create and update issues, add comments, and perform workflow transitions. \n - Sanitization: The script uses
yaml.safe_loadfor parsing local files and coerces field types, but does not perform specific sanitization of the natural language content returned from Jira to prevent injection.
Audit Metadata