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

AdaL

SylphAI's coding agent for the terminal and browser, built on AdalFlow.

SylphAI

How skills run on AdaL

AdaL edits code, debugs, searches the web, and manages MCP servers from a terminal session or its web IDE. Skills extend it through markdown files, which means installed skill text carries the same reach as the agent's own instructions.

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 AdaL

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 AdaL 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