skills/dmytri/shipshape/boatswain/Gen Agent Trust Hub

boatswain

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute various shell commands for repository inspection and management, including git status, git diff, git log, git add, git commit, and cat.
  • [COMMAND_EXECUTION]: The agent is instructed to read command definitions from a local file (RIGGING.md) and execute them (e.g., <lint>, <typecheck>, <plank-inventory>). This mechanism allows the skill to adapt to project-specific tooling but relies on the integrity of the local configuration files.
  • [SAFE]: The skill implements a 'content-blind' policy for the CAPTAIN.md file, explicitly instructing the agent to use git pathspec exclusions (:!CAPTAIN.md) and avoid reading the file's content to maintain a privacy and security boundary between different agent roles.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 05:05 PM
Security Audit — agent-trust-hub — boatswain