Scan history + index for chronic patterns: ghost initiatives
AI agents call get_decision_signature to retrieve information from Mk Plan Master without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool scans historical data and indexes to identify patterns (ghost initiatives) but does not create, modify, delete, or execute external operations. It performs a passive analysis query against existing data, classifying it as a Read operation. The blast radius is low as it only retrieves analytical insights without side effects.
From the tool's definition Tool name 'get_decision_signature' and description 'Scan history + index for chronic patterns: ghost initiatives' indicate data retrieval and analysis operations.
Attacks that exploit this kind of access
Scan history + index for chronic patterns: ghost initiatives. It is categorised as a Read tool in the Mk Plan Master MCP Server, which means it retrieves data without modifying state.
Register the Mk Plan Master MCP server in PolicyLayer and add a rule for get_decision_signature: 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 Mk Plan Master. Nothing to install.
get_decision_signature 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 get_decision_signature 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 get_decision_signature. 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.
get_decision_signature is provided by the Mk Plan Master MCP server (kao273183/mk-plan-master). 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 →