AI agents call find_task to retrieve information from Proofhub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries existing task data across todolists and returns matching results. It has no side effects, does not modify, delete, execute, or create any data. The default fallback to context is a safe parameter behavior. Search/find operations are categorized as Read with low severity since misuse would only reveal existing information.
From the tool's definition Tool description states it 'Search[es] for tasks by title substring' — a search operation that retrieves data without modification. The name 'find_task' and verb 'search' confirm read-only intent.
Attacks that exploit this kind of access
Search for tasks by title substring across all todolists in a project. project defaults to context. It is categorised as a Read tool in the Proofhub MCP Server, which means it retrieves data without modifying state.
Register the Proofhub MCP server in PolicyLayer and add a rule for find_task: 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 Proofhub. Nothing to install.
find_task 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 find_task 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 find_task. 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.
find_task is provided by the Proofhub MCP server (yashmody/proofhub-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 →