AI agents call scan_text_for_secrets to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs detection and analysis of text content to identify secret patterns. It has no side effects: it does not create, modify, delete, execute, or move resources. The operation is read-only pattern matching. While the subject matter (secrets) is sensitive, the tool itself is defensive and non-destructive.
From the tool's definition Tool 'scans' text for patterns and 'returns redacted output' — a passive analysis operation that retrieves information about potential secrets without modifying data, executing code, or triggering external actions.
Attacks that exploit this kind of access
Scan text for secret patterns (API keys, tokens, private keys). Returns redacted output — never raw secrets. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for scan_text_for_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 Todos. Nothing to install.
scan_text_for_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_text_for_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_text_for_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_text_for_secrets is provided by the Todos MCP server (@hasna/todos). 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 →