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

Junie

JetBrains coding agent that works from the IDE, terminal, and CI/CD pipelines.

JetBrains

How skills run on Junie

Junie plans a task, edits project files, runs the debugger and tests, and can open pull requests from CI. Skills it loads carry standing instructions into all of those surfaces, which is exactly the leverage an attacker wants inside a build pipeline.

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 Junie

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 Junie 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