AI agents call browser_sec_get_csp_violations to retrieve information from Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves previously captured Content Security Policy violation logs from the browser's diagnostic state. It performs a read-only query of existing security event data without creating, modifying, deleting, or executing any operations. The low severity reflects that CSP violation logs are observational data unlikely to cause harm if misused by an AI agent.
From the tool's definition Tool name contains 'get' and description states 'Get captured CSP violations', indicating data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get captured CSP violations (see browser_docs). It is categorised as a Read tool in the Browser MCP Server, which means it retrieves data without modifying state.
Register the Browser MCP server in PolicyLayer and add a rule for browser_sec_get_csp_violations: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Browser. Nothing to install.
browser_sec_get_csp_violations is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the browser_sec_get_csp_violations rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for browser_sec_get_csp_violations. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
browser_sec_get_csp_violations is provided by the Browser MCP server (ricardodeazambuja/browser-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →