jira-start
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external source (JIRA ticket summaries and descriptions) to generate git branch names.
- Ingestion points: Fetches ticket data via JIRA MCP tools (SKILL.md, Step 2).
- Boundary markers: None provided for external data content.
- Capability inventory: Performs git branch operations (
git switch,git branch) and JIRA state changes (transition,assign). - Sanitization: Instructions require the agent to transform the ticket title into a 'kebab-case slug', which serves as a natural sanitization step for shell-safe strings.
- [COMMAND_EXECUTION]: The skill uses local git tools and JIRA API tools to modify state. It includes a mandatory 'Step 7 — Confirm before acting' phase where a human must review and approve the planned actions via the
AskUserQuestiontool before any changes are executed.
Audit Metadata