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

Pi

Minimal terminal agent harness with a four-tool core and extensions.

Earendil Works

How skills run on Pi

Pi ships Read, Write, Edit, and Bash as its core tools, then extends itself at runtime through TypeScript extensions, prompt templates, and skills. That extension model is the point of the tool and also the opening, since a skill can add behavior nobody reviewed.

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 Pi

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 Pi 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