High-risk tools in Nogra
6 of the 45 tools in Nogra 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
-
agent_exec_packetExecuteagent_exec_packet
-
chain_pm_then_agentExecutechain_pm_then_agent
-
codex_dispatchExecuteRun formal Codex PM through local Codex OAuth/session with bounded dispatch receipts.
-
codex_dispatch_packetExecuteBuild a formal Codex PM dispatch packet without invoking execution.
-
codex_fresh_eyesExecuteRun /codex fresh-eyes through local Codex OAuth/session using MCP context resources.
-
codex_fresh_eyes_packetExecuteBuild a raw-context packet for /codex or /codex full without invoking execution.
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.