尝试从JS源码和Runtime中提取加密密钥、IV、盐值等关键参数
AI agents call crypto_extract_key to retrieve information from Js Reverse without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves cryptographic keying material from application code and memory. While it accesses sensitive information (keys, IVs, salts), the action itself is informational—it queries and extracts data without side effects. It does not execute code, modify state, delete data, or move funds.
From the tool's definition Tool name 'crypto_extract_key' and description state it 'extracts cryptographic keys, IVs, salts and critical parameters from JS source code and runtime' — purely retrieves sensitive data without modification or execution of external commands.
Attacks that exploit this kind of access
尝试从JS源码和Runtime中提取加密密钥、IV、盐值等关键参数. It is categorised as a Read tool in the Js Reverse MCP Server, which means it retrieves data without modifying state.
Register the Js Reverse MCP server in PolicyLayer and add a rule for crypto_extract_key: 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 Js Reverse. Nothing to install.
crypto_extract_key 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 crypto_extract_key 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 crypto_extract_key. 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.
crypto_extract_key is provided by the Js Reverse MCP server (jenn619/js-reverse-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 →