Manage the john.pot file containing cracked passwords
AI agents call john_pot to retrieve information from John The Ripper without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool manages the john.pot file, which stores previously cracked plaintext passwords. 'Manage' could mean read, list, or also modify/clear the file. Given the ambiguity, the most likely primary use is reading/listing cracked passwords, but it could also write or destructively clear the pot file.
From the tool's definition 'Manage the john.pot file containing cracked passwords' - 'manage' is ambiguous but the pot file is a record of already-cracked passwords
Attacks that exploit this kind of access
Manage the john.pot file containing cracked passwords. It is categorised as a Read tool in the John The Ripper MCP Server, which means it retrieves data without modifying state.
Register the John The Ripper MCP server in PolicyLayer and add a rule for john_pot: 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 John The Ripper. Nothing to install.
john_pot 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 john_pot 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 john_pot. 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.
john_pot is provided by the John The Ripper MCP server (schwarztim/sec-john-the-ripper-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 →