删除任务依赖关系。删除后自动检查下游任务是否可以开始执行。
AI agents call remove_dependency to permanently remove resources in Agent-Comm-Hub — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly deletes a dependency relationship between tasks. Removing a dependency is not trivially reversible (the original dependency definition must be re-added manually), and it automatically triggers downstream task execution checks that could cause unintended tasks to begin running.
From the tool's definition 删除任务依赖关系 (Delete task dependency relationship) — the tool removes/deletes a dependency link between tasks, which is an irreversible structural change to the pipeline.
Attacks that exploit this kind of access
删除任务依赖关系。删除后自动检查下游任务是否可以开始执行。. It is categorised as a Destructive tool in the Agent-Comm-Hub MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agent-Comm-Hub MCP server in PolicyLayer and add a rule for remove_dependency: 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 Agent-Comm-Hub. Nothing to install.
remove_dependency is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_dependency 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 remove_dependency. 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.
remove_dependency is provided by the Agent-Comm-Hub MCP server (liuboacean/agent-comm-hub). 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 →