Parameter "providerToken" invites an agent to pass a credential or personal identifier as a tool argument, where it can be logged or exfiltrated. Confirm this data is truly required and never echoed.
connect_broker · field inputSchema.properties.providerTokenproviderToken
Tool "create_account" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.
create_account · field annotations{}
Tool "update_trade" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.
update_trade · field annotations{}
Tool "delete_trade" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.
delete_trade · field annotations{}
Tool "delete_trades" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.
delete_trades · field annotations{}
Tool "modify_position" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.
modify_position · field annotations{}
Tool "create_price_alert" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.
create_price_alert · field annotations{}
Tool "create_trendline_alert" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.
create_trendline_alert · field annotations{}
Tool "update_alert" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.
update_alert · field annotations{}
Tool "delete_alert" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.
delete_alert · field annotations{}
Tool "create_indicator_alert" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.
create_indicator_alert · field annotations{}
Tool "update_indicator_alert" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.
update_indicator_alert · field annotations{}
Tool "delete_indicator_alert" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.
delete_indicator_alert · field annotations{}
This is an automated, point-in-time report from passive metadata analysis (the server's own initialize and tools/list advertisement). No tools were invoked. The grade reflects deterministic checks only; findings marked "llm" are triage signals for human review and do not affect the grade. Verify any finding with its reproduce command. Rulepack rulepack-2026.08.1.