skills/davidlee/doctrine/worktree/Gen Agent Trust Hub

worktree

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a variety of shell commands to manage the git environment.
  • Git Operations: Uses git rev-parse, git status, git worktree add, and git commit to verify and manipulate the workspace state.
  • Vendor Tooling: Executes the doctrine CLI utility (a resource associated with the author 'davidlee') to perform specialized worktree operations like fork, coordinate, and provision.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local file system and repository state which could theoretically contain malicious instructions.
  • Ingestion points: Reads repository status via git status --porcelain, and parses project files such as plan.toml and .worktreeinclude (documented in SKILL.md).
  • Boundary markers: The skill attempts to mitigate risks by instructing the agent to export DOCTRINE_WORKER=1, which enables internal guards in the doctrine tool to refuse unauthorized writes.
  • Capability inventory: Includes file system access, branch creation, and the execution of project-provided verification commands (e.g., doctrine check gate) across all scripts.
  • Sanitization: The skill relies on the underlying git and doctrine binaries to validate arguments and file paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 01:22 PM
Security Audit — agent-trust-hub — worktree