{"data":{"slug":"securelayer7-promptpurify","name":"PROMPTPurify","tagline":"Prompt-injection guardrail for LLM applications","github_url":"https://github.com/securelayer7/PROMPTPurify","owner":"securelayer7","repo":"PROMPTPurify","owner_avatar_url":"https://avatars.githubusercontent.com/u/14994455?v=4","primary_language":"TypeScript","stars":79,"forks":20,"topics":["ai-firewall","ai-safety","ai-security","application-security","ctf","guardrails","jailbreak-detection","llm-guardrails","llm-security","prompt-engineering","prompt-injection","prompt-injection-detection","security"],"archived":false,"github_pushed_at":"2026-05-31T13:46:19+00:00","maintenance_label":"Slowing","stars_delta_30d":4,"url":"https://www.graphcanon.com/tools/securelayer7-promptpurify","markdown_url":"https://www.graphcanon.com/tools/securelayer7-promptpurify.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/securelayer7-promptpurify","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=securelayer7-promptpurify","description":"Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: anton.securelayer7.net","homepage_url":"https://anton.securelayer7.net","license":"MIT","open_issues":0,"watchers":1,"ai_summary":"Provides an ai-safety solution focusing on jailbreak-detection and prompt-injection-protection for llm-guardrails.","readme_excerpt":"## License\n\nMIT for the SDK and the model weights. Benchmark sources we evaluate\nagainst are listed in\n[training/CORPUS_LICENSES.json](training/CORPUS_LICENSES.json).\n\nSecurity disclosures: [SECURITY.md](SECURITY.md).","github_created_at":"2026-05-16T22:33:22+00:00","created_at":"2026-07-15T10:44:15.60546+00:00","updated_at":"2026-09-20T04:26:19.72483+00:00","categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"ai-firewall","name":"ai-firewall"},{"slug":"ai-safety","name":"ai-safety"},{"slug":"ai-security","name":"ai-security"},{"slug":"application-security","name":"application-security"},{"slug":"ctf","name":"ctf"},{"slug":"guardrails","name":"guardrails"},{"slug":"jailbreak-detection","name":"jailbreak-detection"},{"slug":"llm-guardrails","name":"llm-guardrails"}],"trust":{"provenance":{"is_fork":false,"github_id":1241048131,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-13T06:00:17.747Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":104,"last_release_at":"2026-05-30T05:11:44Z","stars_delta_30d":4,"open_issues_delta_30d":0},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":2,"high_count":0,"last_scan_at":"2026-07-15T10:44:16.883Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-13T06:00:18.242Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-13T06:00:18.242Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-13T06:00:18.242Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-13T06:00:18.242Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"The SDK and model weights of PROMPTPurify come under the MIT license, allowing free usage. However, the full extent of features or services might require a premium setup."},"requirements":{"notes":["- This tool is built with TypeScript.","- Ensure familiarity with TypeScript for efficient integration."]},"constraints":{"pricing_model":"freemium"},"when_to_use":["- When you require compact model solutions that outperform larger open-source guards.","- If your application demands prompt-injection detection, especially in contexts where AI security is paramount like in CTF events."],"when_not_to_use":["- Avoid using PROMPTPurify if your project requires regex or signature-based methods for security purposes, as this tool does not support them.","- Do not use it if you are looking for comprehensive AI-security solutions that extend beyond prompt injection and jailbreak detection."],"source":"enrich:decision_facts","observed_at":"2026-07-16T19:03:13.441Z"},"constraint_facets":{"pricing_model":"freemium"},"decision_summary":[{"label":"Pricing","value":"freemium - The SDK and model weights of PROMPTPurify come under the MIT license, allowing free usage. However, the full extent of features or services might require a premium setup."},{"label":"Requirements","value":"- This tool is built with TypeScript.; - Ensure familiarity with TypeScript for efficient integration."},{"label":"Adopt for","value":"PROMPTPurify, licensed under MIT, provides an ai-safety solution with a focus on jailbreak-detection and prompt-injection-protection for LLM applications without relying on regex or signatures."}]}}