{"id":"0ea36ddd-6c15-4217-9a34-a8fe2647cbb7","slug":"seojoonkim-prompt-guard","name":"prompt-guard","description":"600+ pattern AI agent security defense covering prompt injection, supply chain injection, memory poisoning, action gate bypass, unicode steganography, and cascade amplification. Optional API for early-access and premium patterns. Tiered loading, hash cache, 11 SHIELD categories, 10 languages.","canonicalUrl":"https://www.xpersona.co/mcp/seojoonkim-prompt-guard","sourceUrl":"https://github.com/seojoonkim/prompt-guard","homepage":null,"source":"GITHUB_REPOS","vendor":{"slug":"seojoonkim","label":"Seojoonkim","url":"https://github.com/seojoonkim/prompt-guard"},"protocols":["MCP"],"capabilities":["matches","critical","detects"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-02-25T04:09:46.594Z","freshnessLabel":"Feb 25, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"MCP"},{"label":"Freshness","value":"Feb 25, 2026"},{"label":"Vendor","value":"Seojoonkim"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"docs_crawl","category":"integration","label":"Crawlable docs","value":"6 indexed pages on the official domain","href":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceUrl":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceType":"search_document","confidence":"medium","observedAt":"2026-04-15T05:03:46.393Z","isPublic":true},{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Seojoonkim","href":"https://github.com/seojoonkim/prompt-guard","sourceUrl":"https://github.com/seojoonkim/prompt-guard","sourceType":"profile","confidence":"medium","observedAt":"2026-02-25T04:09:47.871Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"MCP","href":"https://www.xpersona.co/api/v1/agents/seojoonkim-prompt-guard/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/seojoonkim-prompt-guard/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-02-25T04:09:47.871Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"95 GitHub stars","href":"https://github.com/seojoonkim/prompt-guard","sourceUrl":"https://github.com/seojoonkim/prompt-guard","sourceType":"profile","confidence":"medium","observedAt":"2026-02-25T04:09:47.871Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/seojoonkim-prompt-guard/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/seojoonkim-prompt-guard/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["95 GitHub stars","Trust evidence available"],"agentCard":{"name":"prompt-guard","description":"600+ pattern AI agent security defense covering prompt injection, supply chain injection, memory poisoning, action gate bypass, unicode steganography, and cascade amplification. Optional API for early-access and premium patterns. Tiered loading, hash cache, 11 SHIELD categories, 10 languages.","source":"GITHUB_REPOS","sourceId":"github:1145267182","repository":"https://github.com/seojoonkim/prompt-guard","documentation":"https://www.xpersona.co/mcp/seojoonkim-prompt-guard/agent/seojoonkim-prompt-guard","protocols":["MCP"],"capabilities":["matches","critical","detects"],"languages":["typescript"],"install":{"command":"git clone https://github.com/seojoonkim/prompt-guard.git","ecosystem":"git"},"examples":[{"kind":"example","language":"python","snippet":"from prompt_guard import PromptGuard\n\n# API enabled by default with built-in beta key — just works\nguard = PromptGuard()\nresult = guard.analyze(\"user message\")\n\nif result.action == \"block\":\n    return \"Blocked\""},{"kind":"example","language":"python","snippet":"guard = PromptGuard(config={\"api\": {\"enabled\": False}})\n# or: PG_API_ENABLED=false"}]}}