work-in-branch

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard git commands (e.g., git branch -a) to inspect the project environment and manage branches. These operations are aligned with the skill's primary purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads branch names from the environment to determine naming conventions. While this constitutes processing untrusted data, the risk is minimized as the data is only used to suggest names to the user, and the skill explicitly mandates human confirmation before performing any actions (creating or pushing branches).
  • Ingestion points: Reads output from git branch -a to analyze existing branch names (SKILL.md).
  • Boundary markers: Not explicitly defined in the prompt instructions.
  • Capability inventory: Uses git tools to create and push branches (SKILL.md).
  • Sanitization: Relies on human review and confirmation of proposed branch names before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 07:05 AM
Security Audit — agent-trust-hub — work-in-branch