AI agents call scan_secrets to retrieve information from Secscan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and analyzes information about potential security issues; it does not execute code, modify files, delete data, or commit financial transactions. The output is informational (findings about secrets), with no side effects on the codebase or system. Even if misused by an AI agent, it would only report findings, not expose or exfiltrate secrets itself. Classified as Read with low severity.
From the tool's definition Tool scans for hardcoded secrets without modifying or executing code. The description states 'Detect hardcoded secrets and credentials in a directory' — a passive detection activity.
Attacks that exploit this kind of access
Detect hardcoded secrets and credentials in a directory. It is categorised as a Read tool in the Secscan MCP Server, which means it retrieves data without modifying state.
Register the Secscan MCP server in PolicyLayer and add a rule for scan_secrets: 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 Secscan. Nothing to install.
scan_secrets 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 scan_secrets 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 scan_secrets. 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.
scan_secrets is provided by the Secscan MCP server (openjkai/secscan_mcp). 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 →