The Grade Report: weekly grades in your inbox. Subscribe →
The Grade Report

claude-skill

openai.yaml

DRisky

cockpit-dev/cockpit

interface: displayname: "Cockpit" shortdescription: "Develop and validate live applications with Cockpit" default_prompt: "Use $cockpit to inspect, control, and verify this application with live evidence."

openai.yaml got grade D on our automated scan on 2026-10-27.

Why this grade

  • Tells the agent to skip permissions or safety checks.
  • Runs commands with sudo.
  • Runs commands with sudo.
  • Runs commands with sudo.
  • Tells the agent to skip permissions or safety checks.
  • Tells the agent to skip permissions or safety checks.
  • Tells the agent to skip permissions or safety checks.

What grade D means · How the scan works

Before you install

  1. Read any scripts this skill ships.
  2. Note every URL it fetches.
  3. Check allowed-tools and hooks.

Embed this grade

Add this badge to your README. It shows the current grade from CheckSkills.

CheckSkills grade D

Report this skill if the grade looks wrong, or if something slipped through.

Related

DRiskyclaude-skill

update-docs.py

scute-sh/scute

from pathlib import Path import requests

Tells the agent to skip permissions or safety checks.

    DRiskyclaude-skill

    DONE

    TheMostlyGreat/mythos

    Entry: verify.md exists in ticket folder (written by /verify in the verify phase).

    Tells the agent to skip permissions or safety checks.

      DRiskyclaude-skill

      --- a/lib/mpltoolkits/mplot3d/art3d.py +++ b/lib/mpltoolkits/mplot3d/art3d.py @@ -82,6 +82,7 @@ class Line3D(lines.Line2D):

      Tells the agent to skip permissions or safety checks.

        DRiskyclaude-skill

        k.html

        airgap/NavGator

        html,body{margin:0;background:#fff}

        HTML comment contains hidden instructions.