AI agents call get_task_commits to retrieve information from Nubis without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns historical git commit metadata associated with a task. It performs read-only operations with no side effects, reversible actions, code execution, data destruction, or financial impact. The low severity reflects minimal blast radius if misused by an AI agent—worst case being information disclosure of commit history already linked to internal tasks.
From the tool's definition Tool description states 'Get all git commits linked to a task' and retrieves 'commit SHA, message, author, and date'—pure data retrieval with no modification, creation, deletion, or execution of external operations.
Attacks that exploit this kind of access
Get all git commits linked to a task. Shows commit SHA, message, author, and date. It is categorised as a Read tool in the Nubis MCP Server, which means it retrieves data without modifying state.
Register the Nubis MCP server in PolicyLayer and add a rule for get_task_commits: 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.
get_task_commits 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 get_task_commits 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 get_task_commits. 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.
get_task_commits 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 →