High-risk tools in AGI-MCP
5 of the 16 tools in AGI-MCP 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
-
execute_atlas_taskExecuteExecute a task using the ATLAS 5-step process (Analyze, Task Breakdown, Learn, Act, Synthesize)
-
execute_commandExecuteExecute a command and record it in memory
-
execute_skillExecuteExecute a skill to orchestrate subagents and automate complex workflows. Skills can route tasks to specialized agents and coordinate multi-step processes.
-
execute_subagentExecuteExecute a specific subagent for specialized tasks. Subagents are isolated AI assistants with specific capabilities.
-
process_goal_with_gotchaExecuteProcess a goal through all GOTCHA framework layers
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.