AI Skills Security
The SKILL mechanism lets an AI application load reusable capability modules — install and go, take them or leave them. But precisely because “install a SKILL” is such a low-friction action, its metadata declarations, permission requests and distribution path all become entry points: a user who thinks they installed a formatter may in fact have granted something that reads local files or makes outbound network calls.
This section covers SKILL fundamentals, metadata risk, over-permissioning, ways to identify malicious skills and supply-chain attacks, and hands-on deployment of detection tooling.
This section currently holds the articles below, in suggested reading order.
-
SKILL Security Risk Practices
SKILLs, as agent capabilities, are becoming increasingly common, and the number of related skills is growing. According to statistics, most skills on the market contain s…
-
Skill Security Series - Skill Basics
Before summarizing the risks associated with Skills, let's first take a look at what a Skill is through this article to gain a basic understanding.
-
Skill Security Series — Malicious Skills
Among the OWASP Top 10 risks for Skills, malicious skills rank first and are classified as critical. In Agent systems, the agent typically inherits the host machine's use…
-
Skill Security Series - Supply Chain Attack
Skills also have a supply chain. For example, a Skill may include scripts that import malicious third-party libraries, or a Skill may invoke third-party tools through sem…
-
Skill Security Series — Excessive Permissions
Excessive skill permissions refer to when a skill's granted permissions are far beyond what it actually needs. For example:
-
Skill Security Risk: Metadata Security
In the Skill Basics article, we learned that the content between --- in a SKILL.md file is Skill metadata. This metadata typically defines various descriptive information…
-
Defending Against Malicious Skills: SkillSpector Deployment and Detection
SkillSpector is an open-source Skill security scanning tool developed by NVIDIA, with the following features: