VerityLayer check · verification

Prompt-injection detection

Detect injection and manipulation in untrusted text or tool output before you act on it.

What it does

Screen anything your agent ingests from the outside — web pages, emails, docs, tool results — for instruction-override, jailbreaks, persona-switching, and multilingual attacks.

verdictthreat_scoretechniquesreasonsrecommended_action
TierPrice (USDC/Base)Depth
quick$0.02fast
standard$0.06fast
pro$0.15fast
curl -X POST https://suite.veritylayer.dev/sentinel/quick \
  -H "content-type: application/json" \
  -d '{"content": "…", "context": "…"}'
# unpaid → HTTP 402 (x402 challenge); pay $0.02 USDC on Base and retry
Every verdict is signed. This check returns an Ed25519-signed receipt — portable proof of exactly what VerityLayer said. See it, and break one yourself →
← all VerityLayer checks