speckit-taskstoissues
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): The skill possesses an Indirect Prompt Injection surface (Category 8) by processing task definitions from tasks.md to create GitHub issues. 1. Ingestion points: specs//tasks.md and repository remote URL. 2. Boundary markers: Absent. 3. Capability inventory: Execution of local bash scripts and GitHub CLI (gh issue create). 4. Sanitization: The workflow mentions escaping single quotes for arguments.
- COMMAND_EXECUTION (SAFE): The skill executes a local script and uses standard git and gh command-line tools as part of its primary functionality.
Audit Metadata