to-issues
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill operates on external artifacts like plans and specs. This is a standard workflow but introduces a surface for indirect prompt injection.\n
- Ingestion points: Project artifacts (plans, PRDs, specs) specified in Step 1.\n
- Boundary markers: No explicit delimiters or isolation instructions are provided for processed data.\n
- Capability inventory: GitHub CLI (
gh), GitLab CLI, and local file system writes to the.scratch/directory.\n - Sanitization: No specific content sanitization or validation steps are prescribed for source documents.\n- [COMMAND_EXECUTION]: The skill utilizes standard project management CLI tools, specifically the GitHub CLI (
gh) and GitLab CLI, to publish issues to active trackers. These actions are consistent with the skill's stated purpose and use existing environment tools.
Audit Metadata