Extract hashes from various file types using John\
AI agents call john_hash_extract 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 performs data extraction (a read operation) from files to retrieve password hashes. While extracting hashes themselves is non-destructive, the medium severity reflects that hash extraction could facilitate subsequent password cracking attacks if combined with sibling tools like 'john_crack' on the same server. The tool has no direct side effects on the source files or systems.
From the tool's definition Tool name 'john_hash_extract' and description 'Extract hashes from various file types' indicates retrieval/querying of hash data from files without modification.
Attacks that exploit this kind of access
Extract hashes from various file types using John\. 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_hash_extract: 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_hash_extract 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_hash_extract 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_hash_extract. 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_hash_extract 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 →