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

bosun

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard Git commands (git status, git diff, git log, git commit) and executes local project-defined verification scripts (e.g., tests or linters). These operations are restricted to the local development environment and are essential for the skill's stated purpose of repository hygiene.
  • [DATA_EXFILTRATION]: The skill contains a 'Boundaries' section that explicitly forbids pushing to remotes, creating/pushing tags, publishing packages, or creating releases. These constraints effectively mitigate the risk of unauthorized data transmission.
  • [PROMPT_INJECTION]: The instructions are clear and follow a constrained role-play structure ('Bosun'). The skill does not contain any language intended to bypass safety guardrails, override prior instructions, or extract system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 06:56 PM
Security Audit — agent-trust-hub — bosun