jira-safe
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides multiple Node.js (
.mjs) and Python (.py) scripts designed to be executed by the agent to automate Jira workflows, including a bulk deletion utility that performs recursive deletes of project issues. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to how it processes and stores user-controlled data.
- Ingestion points: Untrusted data enters the skill context through the
taskobject in thefullWorkflowCycleand through task/story definitions in the management scripts. - Boundary markers: The skill lacks boundary markers or explicit instructions to the model to ignore embedded commands within the processed data.
- Capability inventory: The skill possesses extensive write capabilities, including issue creation, state transitions, and bulk deletion via the Jira REST API using authenticated HTTP requests.
- Sanitization: No sanitization or filtering is applied to user-supplied text before it is transformed into Atlassian Document Format (ADF) for storage, meaning malicious instructions stored in Jira could influence future agent operations.
Audit Metadata