reuse-worktree

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local git commands (git fetch, git reset, and git checkout) to synchronize the repository with the main branch and manage branches.
  • [INDIRECT_PROMPT_INJECTION]: The skill interpolates the $ARGUMENTS variable directly into the git checkout -b command. This represents an attack surface where a maliciously crafted branch name could attempt to execute additional commands via shell metacharacters. 1. Ingestion points: User-provided input via the $ARGUMENTS variable in SKILL.md. 2. Boundary markers: No delimiters or markers are used to isolate the variable from the surrounding shell command. 3. Capability inventory: The skill has the capability to execute shell commands via the git CLI. 4. Sanitization: The skill instructions do not perform validation or sanitization of the $ARGUMENTS value before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 06:30 AM
Security Audit — agent-trust-hub — reuse-worktree