High-risk tools in Aaaa Nexus
8 of the 9 tools in Aaaa Nexus 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
-
healthExecute 3/5Return worker health and runtime constants.
-
inferenceExecute 3/5Run Llama 3.1 8B inference with anti-hallucination guard and error correction. Returns answer with HELIX metadata. $0.015/call.
-
inference_streamExecute 3/5Streaming CoT inference with Server-Sent Events (SSE). Events: cot/cot_end/ans/done. $0.025/call.
-
metricsExecute 3/5Return platform metrics and endpoint registry.
-
oracle_entropyExecute 3/5Return entropy epoch and nonce seed.
-
oracle_hallucinationExecute 3/5Return hallucination epsilon threshold.
-
ratchetgate_advanceExecute 3/5Advance RatchetGate epoch, re-key session at RG_LOOP=47 boundary. Returns new epoch and key material. $0.005/call.
-
ratchetgate_sessionExecute 3/5Register a RatchetGate session — formally proved MCP session re-key preventing CVE-2025-6514 long-lived credential theft. Returns session_id and next_probe_at. $0.002/call.
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.
More on Aaaa Nexus
Enforce policy on Aaaa Nexus
One command generates a policy scaffold for every server in your MCP config.
npx -y @policylayer/intercept init