wk-jira
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes scoped shell commands for git and GitHub CLI (gh) to retrieve branch information, commit logs, and PR states for synchronization purposes.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from Jira issue descriptions and GitHub PR bodies, creating a potential surface for indirect prompt injection.
- Ingestion points: Data is sourced from git log, gh pr view, and getJiraIssue MCP calls.
- Boundary markers: The instructions recommend using horizontal rules (---) and wrapping existing content to separate external data from agent-authored context blocks.
- Capability inventory: The skill can perform shell commands (git, gh) and Jira write operations (editJiraIssue, transitionJiraIssue).
- Sanitization: Human confirmation is required for irreversible write operations like issue creation and terminal status changes, providing a safety gate against unauthorized modifications.
Audit Metadata