AI agents use link_commit_to_task to create or update resources in Nubis — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nubis environment.
This tool creates or modifies a link/association between a commit and a task, which is a reversible write operation that adds metadata or establishes relationships. It does not execute code, delete data, or move money. The operation is low severity as it only establishes traceability metadata without affecting the actual codebase or destructively altering data.
From the tool's definition Tool description states it 'Link a git commit to a task' and 'Associates code changes with task work', indicating creation or modification of a metadata relationship between existing entities (commits and tasks).
Attacks that exploit this kind of access
Link a git commit to a task for traceability. Associates code changes with task work. It is categorised as a Write tool in the Nubis MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nubis MCP server in PolicyLayer and add a rule for link_commit_to_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 Nubis. Nothing to install.
link_commit_to_task 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 link_commit_to_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 link_commit_to_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.
link_commit_to_task is provided by the Nubis MCP server (@lil2good/nubis-mcp-server). 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 →