AI agents use skill_install_from_git to create or update resources in LocalAnt — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LocalAnt environment.
This tool creates or modifies data (cloning a repository and persisting it to disk) without irreversibly deleting anything, placing it in the Write category rather than Execute or Destructive. However, the fact that it fetches and stores arbitrary code from a git URL presents a medium severity risk—a compromised git repository or man-in-the-middle attack could introduce malicious code into the skills directory.
From the tool's definition Clones a git repository into the skills directory and creates files. The description explicitly states the skill is 'saved DISABLED', indicating the tool modifies the local filesystem by adding new skill code, though with a mitigating control (disabled by…
Attacks that exploit this kind of access
Clone a skill from a git URL into the skills directory (saved DISABLED). It is categorised as a Write tool in the LocalAnt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LocalAnt MCP server in PolicyLayer and add a rule for skill_install_from_git: 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 LocalAnt. Nothing to install.
skill_install_from_git is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the skill_install_from_git 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 skill_install_from_git. 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.
skill_install_from_git is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →