Claude Code
Anthropic's terminal-native coding agent. It loads SKILL.md files automatically every session.
AnthropicHow skills run on Claude Code
Claude Code discovers and runs Agent Skills from your project and personal directories on startup, with no explicit import. That convenience is also the exposure: a single SKILL.md can carry instructions and helper scripts that execute with your shell's privileges the moment the agent picks it up.
Skill security, assessed
Every public skill in our index is assessed by the Anomity Skill Intelligence engine against its real source: remote code execution, credential and data exfiltration, prompt injection, and unsafe installers.
Govern the skill layer on Claude Code
Scanning a skill before use tells you what it claims to do. Anomity's Endpoint Sensor sees what agents actually do at runtime: it discovers every skill, agent, and MCP server on the endpoint, and policy can allow, deny, or log the tool calls a skill triggers on Claude Code and every other agent. Violations route to your SIEM, Slack, email, or Jira with a queryable 90-day audit trail.
Book a 30-minute demo to see your own agent and skill inventory.
