Cheetah Agent Security

Neutral trust and security layer for the agentic internet. Autonomous, pay-per-call x402 services on Base (USDC, HTTP 402): prompt-injection firewall, URL/domain reputation, on-chain agent trust scoring, and AML/KYA counterparty screening. The customer is the agent, not the human. Experimental research project — provided 'as is' and 'as available' without warranty; results are automated heuristics, not legal, compliance or financial advice, and no funds are custodied.

Skills

• Prompt-Injection Firewall
  Self-hosted LLM Guard scan of untrusted text for prompt-injection / jailbreak attempts. Returns safe/verdict/risk_score.
• URL / Domain Reputation
  RDAP + phishing heuristics reputation check for a URL or domain.
• Bulk URL Reputation Feed
  Bulk RDAP + phishing reputation for up to 20 URLs in a single call — the firewall URL check as a data feed for crawlers and pipelines.
• On-Chain Agent Trust Score
  On-chain reputation score (PROCEED/CAUTION/BLOCK) for a Base agent wallet from wallet age, activity, balances and our dispute history.
• AML / KYA Counterparty Screening
  OFAC sanctions + on-chain exposure + internal scam/dispute list screening of a counterparty wallet. Returns CLEAR/REVIEW/BLOCK.
• Agent Deal Escrow
  Escrow state machine for agent-to-agent deals.
• Skill Pre-Install Check
  Static pre-install analysis of a SKILL.md (plus referenced urls/scripts/requested permissions) before install: remote code execution (curl|bash), reverse shells, secret exfiltration, destructive commands, obfuscation and over-broad permissions. Returns VERIFIED/FAILED with evidenced violations.

How to call

https://x402.cheetahsecurity.de

Listed in

Directories this entry was found in.