Audit third-party AI API relay/proxy services for security risks. Detects hidden prompt injection, prompt leakage, instruction override, identity hijacking (Chinese-market substitutes), jailbreak vulnerabilities, context truncation, tool-call package substitution (AC-1.a), error response header leakage (AC-2 adjacent), SSE-level stream integrity anomalies (AC-1 streaming), Web3 prompt injection (SlowMist signature isolation), infrastructure fingerprinting, and latency variance anomalies. Use when: test relay, audit API, audit relay, detect injection, relay security, API relay audit, is this relay safe, does it inject prompts, test proxy API, check API key, 中转站安全, 测试中转站, 中转站审计.
Use when auditing third-party AI API relays, proxy APIs, or API-key resale services for hidden prompt injection, prompt leakage, instruction override, context truncation, tool-call substitution, error leakage, SSE stream anomalies, Web3 wallet-safety prompt injection, infrastructure fingerprints, and latency variance.