Surgical security scan for hardcoded secrets.
AI agents call check_security_leaks to retrieve information from Code-Oracle without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and analyzes code to identify hardcoded secrets but does not modify, execute, or delete anything. It is a detection/auditing function that returns findings without side effects. The low severity reflects that misuse would only involve scanning code the agent has access to, with no destructive, financial, or execution-based consequences.
From the tool's definition Tool performs a 'surgical security scan for hardcoded secrets' - a scanning/detection operation with no modification, deletion, or execution capabilities. The verb 'check' and noun 'scan' indicate passive information retrieval.
Attacks that exploit this kind of access
Surgical security scan for hardcoded secrets. It is categorised as a Read tool in the Code-Oracle MCP Server, which means it retrieves data without modifying state.
Register the Code-Oracle MCP server in PolicyLayer and add a rule for check_security_leaks: 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 Code-Oracle. Nothing to install.
check_security_leaks 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 check_security_leaks 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 check_security_leaks. 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.
check_security_leaks is provided by the Code-Oracle MCP server (sri-lohith-mulugu/oracle-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 →