Cursor: Security for Agents

Security Agents scan your code for security bugs, risky patterns, and vulnerabilities. Cursor ships two managed agent types that cover different moments in the lifecycle: one reviews changes as they come in, the other goes looking for what is already there. The split below is the first decision you make when you set one up.

Both agent types run on the Automations platform and require Cloud AgentsAgents that run in a Cursor-managed virtual machine, check out the repo, do the work and open a pull request, then shut down, with no load on your laptop.. You configure them from the Security Agents Dashboard at cursor.com/dashboard/security-agents, where you create your first agent.

The two agent types take different triggers, which is what makes the Reviewer fit code review and the Scanner fit ongoing coverage. Match the trigger to the agent before you turn anything on.

Each agent has three configuration surfaces: the built-in checks it runs, custom instructions that give it context, and the tools or MCPs it uses to do its work and report findings. They stack, so a single agent can run a tuned set of checks, follow project-specific guidance, and push results into the system your team already uses.

Tools and MCPs are how a Security Agent connects to where your team tracks security work. Use them to do three things:

• Send vulnerabilities to a Slack channel, issue tracker, or another connected system.
• Add custom instructions that explain when and how the agent should use each MCPModel Context Protocol. A standard that lets an AI agent pull in context from outside the repo, like Jira tickets or internal docs..
• Give the agent extra context from tools or MCPs before it reports a finding.

You don't have to wait for a pull request. Use the /review-security or /review skills to run the Security Agent from your agent before you push the code, so you catch findings while the change is still local.

• What diff is reviewed: by default, /review-security reviews your branch changes, meaning every change relative to the base branch, including committed and uncommitted changes. Ask it to review only your uncommitted changes when you want narrower feedback.
• Against which branch: /review-security compares against your default base branch. When your base branch isn't the default (such as main), tell the agent which branch to compare against or let it infer from the context.

Security Agents are billed at the team usage level. Usage is charged to the team's usage pool, and agents run under a shared team service account, so they don't affect any individual user's usage.

For measurement, Security Agents track three key metrics across runs. To decide whether an issue was fixed, Cursor uses LLMs to review incremental diffs and assess whether the flagged issue was resolved.

Every agent run is tracked in the dashboard. The run history shows when an agent ran, which tools it used, its final status, and how long it took. Open a run to inspect the underlying Cloud Agent for more detail about what the agent did.