AI agents call audit_secrets to retrieve information from Prompts without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read/scan operation over code to detect secrets and sensitive data. It does not modify, delete, or execute anything — it only audits and reports findings. Severity is medium because it reads potentially sensitive source code and could expose secret locations, but it is fundamentally a passive scan.
From the tool's definition 扫描代码中的密钥、Token、密码等隐私信息 (scans code for keys, tokens, passwords and other private information)
Attacks that exploit this kind of access
【隐私审计】扫描代码中的密钥、Token、密码等隐私信息。发布前必须调用，有 critical/high 发现时拦截发布。. It is categorised as a Read tool in the Prompts MCP Server, which means it retrieves data without modifying state.
Register the Prompts MCP server in PolicyLayer and add a rule for audit_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 Prompts. Nothing to install.
audit_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 audit_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 audit_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.
audit_secrets is provided by the Prompts MCP server (thana0623/pmcp-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 →