Is this AI skill safe to install?
Agent skills can run code, read files and reach the internet. Paste a GitHub link and get a safety grade in seconds: prompt injection, hidden characters, credential access, risky commands and more.
See exactly what we check and how the grade is calculated on the methodology page.
Popular vetted skills
35 skills scanned so far
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results,…
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, o…
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable…
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Need more than an automated scan?
Our full review is a line-by-line human audit with a sandboxed test run. Skill authors get a "Reviewed" badge; teams get a clear yes or no before rolling a skill out.