Snyk the leader in secure AI software development, empowers organizations to build fast and stay secure by unleashing developer productivity and reducing business risk. The company’s AI Security Platform seamlessly integrates into developer and security workflows to accelerate secure software delivery in the AI Era. Snyk delivers trusted, actionable insights and automated remediation, enabling modern organizations to innovate without limits and secure AI-driven software for over 4,500 customers.
This is the 9th launch from Snyk. View more
Skill Inspector
Launching today
Skill Inspector helps you analyze and understand the capabilities, risks, and behaviors of AI skills before they reach production. It inspects how skills are defined, what tools and permissions they rely on, and how they behave across different scenarios. Whether you're building copilots or AI-powered apps, Skill Inspector gives you the visibility and confidence to ship AI safely. Identify risky patterns, validate skill behavior, and ensure your AI does exactly what you expect - no surprises.
Free
Launch Team / Built With
Snyk
@liran_tal Honest question, does this catch skills that look fine statically but fetch remote configs or schemas at runtime? That's been the scarier case for me. The manifest says it reads from a local file, then at runtime it pulls a URL you never reviewed.
Snyk
@whetlan the work on the Skill Inspector app is based on very extensive data benchmark and tuning we ran back in February for the ToxicSkills research. It's available here for review: https://github.com/snyk/agent-scan/blob/main/.github/reports/skills-report.pdf
You can go ahead and test the skill audit right there from the interactive and free web app for Skill Inspector and if you find that it doesn't catch the agent skill instructions that you're concerned about. If we don't flag anything there and you can share the skill package with me please do, I'll add it to our dataset so we can add and improve it :)