Now in early access, book a 30-minute demo →
Agent Skill security

inference.sh

Agent workspace with a skill registry, tool connectors, and a deploy CLI.

Inference Shell

How skills run on inference.sh

inference.sh runs agents that plan multi-step work, then call tools, flows, and connected accounts through its Belt CLI and skill registry. A skill pulled from the registry becomes instructions the agent trusts, so its content decides which connectors and credentials get exercised.

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.

Browse the Skill Risk Index →

Govern the skill layer on inference.sh

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 inference.sh 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.

Other agents

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok