High-risk tools in Agent Link
3 of the 6 tools in Agent Link are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
replyExecuteReply to an agent that is waiting for clarification. Continues the conversation until the agent returns a result or asks another question.
-
spawn_agentExecuteSpawn an AI agent to work on a task. Returns a question if the agent needs clarification, or a result when done.
-
spawn_agentsExecuteSpawn multiple AI agents in parallel. Each agent runs independently and results are returned together. Great for getting multiple opinions, parallel code reviews, or distributin...
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.