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
Risk Level
SAFE
Analyzed
Jul 2, 2026, 11:05 PM
Security Audit — agent-trust-hub — branch