AI agents invoke foundry_install 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 runs an external git command (git submodule add) to fetch and install third-party code into the project. It executes filesystem and git operations whose effects depend on the provided org/repo argument. Installing arbitrary external dependencies from git repositories poses a high risk: malicious packages could introduce supply-chain attacks, backdoors, or malicious code into the codebase.
From the tool's definition 'Install a dependency via git submodule' — executes a git submodule add operation on the filesystem, triggering external git operations and modifying the repository structure
Attacks that exploit this kind of access
Install a dependency via git submodule. Examples: forge-std, openzeppelin-contracts. Use format: org/repo (e.g.,. 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_install: 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_install 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_install 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_install. 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_install 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 →