pip install agent-trust-sdkVerify agent trustworthiness before they interact with your systems. Detect prompt injection, track reputation, and protect your AI infrastructure.
from agent_trust import AgentTrustClient
client = AgentTrustClient()
# Verify an agent before allowing interaction
result = client.verify_agent(
name="Shopping Assistant",
url="https://shop.ai/agent",
description="I help you find the best deals"
)
if result.is_blocked:
print(f"⛔ Agent blocked: {result.reasoning}")
else:
print(f"✅ Agent trusted (score: {result.trust_score})")Built for the agent-first world where AI systems communicate autonomously
65+ patterns detect prompt injection, jailbreaks, data exfiltration, and social engineering attacks.
Trust scores evolve over time based on real interactions. Good agents build reputation, bad actors get blocked.
One API call to verify. SDKs for Python and TypeScript. Built to work with A2A, LangChain, and more.
Three simple steps to protect your AI infrastructure
Before an external agent interacts with your system, send their agent card to TrustLayer. We scan for malicious patterns and check their reputation.
Receive a verdict (allow/caution/block), threat level, detected patterns, and trust score—all in milliseconds.
After interacting, report the outcome. This builds the reputation network—good agents rise, bad actors get flagged.
Start free, scale as you grow
For side projects and testing
For growing products
For large organizations
Start verifying agents in minutes. No credit card required.