jira-implement-task
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Potential for indirect prompt injection. The skill fetches ticket descriptions from an external source (Jira) and uses them to generate implementation plans and execute code changes. An attacker with access to the Jira ticket could insert malicious instructions that the agent might follow. Ingestion points: Fetches Jira issue data in Step 1: Fetch Ticket Details. Boundary markers: None present; the agent treats the description as authoritative for its implementation plan. Capability inventory: The skill utilizes Bash, Edit, Write, git, and gh tools to modify code and push changes. Sanitization: No sanitization of the ticket body is performed before processing.
- [COMMAND_EXECUTION]: Executes shell commands for version control and testing. It uses git for branch management and commits, gh for pull requests, and allows execution of project-defined test commands such as pnpm test.
Audit Metadata