AI agents call security_scan to retrieve information from Git Steer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Security scanning is fundamentally a Read operation: it queries repositories to identify and report vulnerabilities without modifying code, executing commands, or triggering actions. While the tool operates within a GitHub management system with elevated privileges, its stated function is informational analysis only. The 'detailed fix information' output does not constitute execution of those fixes.
From the tool's definition Tool performs scanning/querying for vulnerabilities with 'detailed fix information' — data retrieval and analysis with no modification or execution. The description uses 'scan' and 'information' language indicating passive assessment.
Attacks that exploit this kind of access
Scan repositories for security vulnerabilities with detailed fix information. It is categorised as a Read tool in the Git Steer MCP Server, which means it retrieves data without modifying state.
Register the Git Steer MCP server in PolicyLayer and add a rule for security_scan: 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 Git Steer. Nothing to install.
security_scan 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 security_scan 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 security_scan. 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.
security_scan is provided by the Git Steer MCP server (ry-ops/git-steer). 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 →