harness-init

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run in scripts/harness_paths.py to execute git commands such as rev-parse and worktree list. These calls are used to identify the repository root and common directory. The implementation uses list-based arguments without a shell, which is a secure practice for command execution.
  • [COMMAND_EXECUTION]: The add_legacy_exclude function modifies the .git/info/exclude file to append patterns for ignoring legacy directories. This is a standard configuration task for managing repository state and does not present a security risk in this context.
  • [DATA_EXFILTRATION]: The skill performs local file migrations and writes metadata to a location.json file. No network operations or external data transmissions were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 02:39 AM
Security Audit — agent-trust-hub — harness-init