{"id":"1ecb4741-0491-4efc-bfd0-c2c9ce5a30dd","slug":"smithery-found402-prompt-injection-detector","name":"prompt-injection-detector","description":"Prompt Injection Detector is a stateless security microservice built for the agent economy. Before your agent acts on any input — whether from a user, an email, a document, or another agent — run it through this scanner first.\nDetects: jailbreak attempts, instruction overrides, role-play manipulation, goal hijacking (OWASP ASI01), tool misuse patterns (OWASP ASI02), hidden instructions embedded in data, and indirect injection via external content.\nReturns a confidence score, severity rating, specific patterns detected, and a clear recommendation — block, warn, or pass.\nPay per scan via x402 protocol. USDC on Base. No API keys. No subscriptions. No human in the loop. Agents call it directly.\nMCP tool name: scan_for_injection","canonicalUrl":"https://www.xpersona.co/mcp/smithery-found402-prompt-injection-detector","sourceUrl":"https://prompt-injection-detector.fly.dev","homepage":"https://prompt-injection-detector.fly.dev","source":"SMITHERY","vendor":{"slug":"fly","label":"Fly","url":"https://prompt-injection-detector.fly.dev"},"protocols":["MCP"],"capabilities":[],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-04-15T00:37:52.481Z","freshnessLabel":"Apr 15, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"MCP"},{"label":"Freshness","value":"Apr 15, 2026"},{"label":"Vendor","value":"Fly"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Fly","href":"https://prompt-injection-detector.fly.dev","sourceUrl":"https://prompt-injection-detector.fly.dev","sourceType":"profile","confidence":"medium","observedAt":"2026-04-15T00:37:52.481Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"MCP","href":"https://www.xpersona.co/api/v1/agents/smithery-found402-prompt-injection-detector/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/smithery-found402-prompt-injection-detector/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-04-15T00:37:52.481Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/smithery-found402-prompt-injection-detector/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/smithery-found402-prompt-injection-detector/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["Trust evidence available"],"agentCard":{"name":"prompt-injection-detector","description":"Prompt Injection Detector is a stateless security microservice built for the agent economy. Before your agent acts on any input — whether from a user, an email, a document, or another agent — run it through this scanner first.\nDetects: jailbreak attempts, instruction overrides, role-play manipulation, goal hijacking (OWASP ASI01), tool misuse patterns (OWASP ASI02), hidden instructions embedded in data, and indirect injection via external content.\nReturns a confidence score, severity rating, specific patterns detected, and a clear recommendation — block, warn, or pass.\nPay per scan via x402 protocol. USDC on Base. No API keys. No subscriptions. No human in the loop. Agents call it directly.\nMCP tool name: scan_for_injection","source":"SMITHERY","sourceId":"smithery:found402/prompt-injection-detector","homepage":"https://prompt-injection-detector.fly.dev","repository":"https://prompt-injection-detector.fly.dev","documentation":"https://www.xpersona.co/mcp/smithery-found402-prompt-injection-detector/agent/smithery-found402-prompt-injection-detector","protocols":["MCP"]}}