manage-worktrees

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to create Git worktrees based on branch names retrieved from the repository environment. This represents an indirect prompt injection attack surface where a malicious branch name (e.g., containing shell metacharacters) could influence the construction of shell commands.\n- Ingestion points: Git branch names retrieved from the current repository state (SKILL.md).\n- Boundary markers: No explicit delimiters or instructions to sanitize or quote branch name variables are provided for the manual fallback commands.\n- Capability inventory: Execution of shell commands via the Git CLI.\n- Sanitization: The workflow does not define explicit validation or escaping for branch name parameters before they are used in manual command construction.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 03:47 AM
Security Audit — agent-trust-hub — manage-worktrees