rhdh-jira-api
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The bundled Python scripts (
scripts/setup.py,scripts/parse_issues.py,scripts/validate_components.py, andscripts/validate_field_ids.py) utilizesubprocess.runto interact with the Atlassian CLI (acli). These calls are implemented using list-based arguments rather than shell strings, and they do not useshell=True, which is the recommended practice for preventing command injection. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Jira issues (such as summaries and descriptions) through
scripts/parse_issues.py. This constitutes an indirect prompt injection surface. The risk is minimized by the skill's focus on structured data extraction and the explicit requirement for user approval for mutations (as documented inSKILL.mdandreferences/rest-api-fallback.md). - [DATA_EXPOSURE]: The skill adheres to secure credential management. It explicitly instructs the agent to avoid reading, printing, or constructing authorization material, relying instead on the
aclitool's native credential store or host-provided authenticated adapters.
Audit Metadata