Agent Input Guard
activePreflight untrusted text for common prompt-injection, credential-exfiltration, and tool-abuse patterns. Deterministic heuristic scan; not a guarantee of safety.
Settled via PayAI.
- Transactions · 30d
- 1
- Volume · 30d
- $0.002
- Unique buyers · 30d
- 1
- Uptime · 30d
- 100.0%
- Latency p50
- 220ms
Endpoints (2 live)
POST/scan— Preflight untrusted text for common prompt-injection, credential-exfiltration, and tool-abuse patterns. Deterministic heuristic scan; not a guarantee of safety. (0.002 USDC on Base)POST/repair— Repair malformed JSON syntax and check optional required top-level keys. No model or full JSON Schema validation. Review changes before use. (0.002 USDC on Base)
First seen · last seen · last active