AI agents call pinned_list_guards to retrieve information from Pinnedai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves information about active guards (regression tests and learned mistakes) stored in the repository. This is a non-destructive read operation with no side effects. Even if an AI misuses it by listing guards, the blast radius is negligible—no data is modified, deleted, or executed. Low severity reflects that unauthorized reading of guard metadata poses minimal risk.
From the tool's definition Tool name contains 'list' and description states 'List the active Pinned guards in the repository' — a query operation that retrieves and displays existing data without modification.
Attacks that exploit this kind of access
List the active Pinned guards in the repository. Use when the user asks. It is categorised as a Read tool in the Pinnedai MCP Server, which means it retrieves data without modifying state.
Register the Pinnedai MCP server in PolicyLayer and add a rule for pinned_list_guards: 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 Pinnedai. Nothing to install.
pinned_list_guards 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 pinned_list_guards 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 pinned_list_guards. 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.
pinned_list_guards is provided by the Pinnedai MCP server (pinnedai/pinnedai). 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 →