immunity-agent is the open-source guard that watches the three places an agent can hurt us: what it does, what it installs, and what it leaves behind. It integrates with more than 55 AI coding tools. Before any command reaches a machine
When a layer is watching every action, secret, package, and fix in real time, we no longer have to stand over an agent's shoulder. We can let it move at full speed while something underneath continuously verifies its work.
Four components share the work: Warden is the rule-keeper. It evaluates every action through deterministic policies backed by AI analysis. Dangerous behavior like destructive commands, reverse shells, or security bypasses can be blocked before execution.
Cloak protects secrets. If an agent tries to expose an API key or password, Cloak catches it before it reaches logs, prompts, or outbound requests.
IAM gives agents only the permissions they need. A research agent can research. A deployment agent can deploy. Nothing gets more access than its role requires.
Semantic Guard focuses on intent. Prompt injection attacks often arrive disguised as normal instructions hidden inside documents or websites. Semantic Guard identifies those attempts and escalates uncertain cases for deeper inspection.
Then there are the packages, where many attacks begin. The immunity CLI wraps installs across pip, npm, and other package managers. Before anything reaches disk, packages are scored and analyzed. Known malicious packages are blocked immediately. Suspicious packages are flagged with clear reasons and safer alternatives whenever possible.
You can dump this skill to your AI coding agent and it'll pick things up