AI agents invoke foundry_update to trigger actions in HashPilot. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a git command (submodule update) that modifies repository state by pulling in new dependency versions. While it can be partially reversed by pinning to previous commits, it triggers external operations and modifies the working environment. It fits Execute best as it runs an external git operation with side effects dependent on the current state of remote repositories.
From the tool's definition 'Update all git submodule dependencies to their latest versions' — runs a git submodule update operation
Attacks that exploit this kind of access
Update all git submodule dependencies to their latest versions. It is categorised as a Execute tool in the HashPilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the HashPilot MCP server in PolicyLayer and add a rule for foundry_update: 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 HashPilot. Nothing to install.
foundry_update is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the foundry_update 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 foundry_update. 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.
foundry_update is provided by the HashPilot MCP server (justmert/hashpilot). 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 →