Tool results (MCP servers, APIs, search, file reads) are untrusted content the agent re-reads. Detects a result that gives orders to the agent, strays from what the tool should return or asks to send data (tool poisoning). Returns allow, review or block.
| Network | Scheme | Amount | Pay To |
|---|---|---|---|
| Base | exact | $0.01 USDC | 0xb36c...54Eb |