branch
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes standard Git commands (git status, branch creation, checkout) to manage task branches, which is the intended and documented behavior.
- [SAFE]: Explicit restrictions are included to prevent dangerous Git operations, such as force pushing to main or master, or amending existing history.
- [SAFE]: No obfuscation, unauthorized network calls, or sensitive file access patterns were identified.
- [PROMPT_INJECTION]: The skill reads task information from external sources like Linear tickets to suggest branch names, representing an indirect prompt injection surface.
- Ingestion points: Linear tickets, Charters, and session state (SKILL.md).
- Boundary markers: None identified in the skill instructions.
- Capability inventory: Git branch creation, checkout, and status reporting (SKILL.md).
- Sanitization: Branch names are constrained to a kebab-case summary format.
Audit Metadata