AI agents invoke check_spec_drift to trigger actions in Scrumdo. 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.
The tool runs a drift check operation (an external analysis process) against a pull request and returns results. This is not a simple data retrieval; it triggers an active execution process. The blast radius is medium since it is read-like in outcome but executes an external operation whose effects depend on the PR state.
From the tool's definition 'Run the drift check on the card's latest PR + return the report' — explicitly triggers an active check/analysis operation against a PR
Attacks that exploit this kind of access
Run the drift check on the card's latest PR + return the report. It is categorised as a Execute tool in the Scrumdo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Scrumdo MCP server in PolicyLayer and add a rule for check_spec_drift: 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 Scrumdo. Nothing to install.
check_spec_drift 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 check_spec_drift 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 check_spec_drift. 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.
check_spec_drift is provided by the Scrumdo MCP server (scrumdollc/scrumdo-mcp). 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 →