{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"smithery_nicks-brn-promptscan","slug":"nicks-brn-promptscan","name":"promptscan","type":"api","url":"https://promptscan.dev","page_url":"https://unfragile.ai/nicks-brn-promptscan","categories":["mcp-servers","deployment-infra"],"tags":["mcp","model-context-protocol","smithery:nicks-brn/promptscan"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"smithery_nicks-brn-promptscan__cap_0","uri":"capability://safety.moderation.prompt.injection.detection","name":"prompt injection detection","description":"This capability scans user inputs, retrieved documents, and tool outputs for potential prompt injection attacks before they are sent to an LLM. It employs a combination of heuristic analysis and pattern recognition to identify suspicious content, returning a score indicating the likelihood of an attack, the type of attack detected, and a sanitized version of the input. This proactive approach helps maintain the integrity of AI interactions by filtering out harmful inputs.","intents":["How can I ensure user inputs are safe before processing them with my AI model?","What methods can I use to detect and mitigate prompt injection attacks in my application?","How do I sanitize user inputs to prevent malicious interactions with my AI agents?"],"best_for":["developers building AI applications requiring secure input handling"],"limitations":["May not catch all sophisticated injection techniques due to evolving attack vectors","Performance may vary based on input complexity and size"],"requires":["Node.js 14+","Access to the PromptScan API"],"input_types":["text"],"output_types":["structured data"],"categories":["safety-moderation","ai-security"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_nicks-brn-promptscan__cap_1","uri":"capability://safety.moderation.attack.type.classification","name":"attack type classification","description":"This capability identifies and classifies the type of prompt injection attack detected, such as SQL injection, command injection, or data exfiltration attempts. By analyzing the structure and semantics of the input, it categorizes the threat, providing developers with actionable insights on the nature of the attack. This classification helps in tailoring responses and defenses against specific vulnerabilities.","intents":["How can I categorize different types of prompt injection attacks in my application?","What specific threats should I be aware of when processing user inputs?","How do I improve my application's security posture by understanding attack types?"],"best_for":["security-focused developers and teams looking to enhance their AI systems"],"limitations":["Classification accuracy may depend on the quality of training data and evolving attack strategies"],"requires":["Node.js 14+","Access to the PromptScan API"],"input_types":["text"],"output_types":["structured data"],"categories":["safety-moderation","ai-security"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_nicks-brn-promptscan__cap_2","uri":"capability://safety.moderation.input.sanitization","name":"input sanitization","description":"This capability sanitizes user inputs by removing or altering potentially harmful content based on the detection results. It employs a set of predefined rules and contextual understanding to ensure that the sanitized text retains its meaning while eliminating malicious components. This process is crucial for maintaining the functionality of AI models while ensuring security.","intents":["How can I clean user inputs to prevent prompt injections while preserving their intent?","What methods are available for sanitizing text before sending it to an AI model?","How do I implement input sanitization in my AI application?"],"best_for":["developers looking to enhance the security of their AI applications"],"limitations":["Sanitization may alter the original meaning of inputs in some cases","Requires careful rule management to avoid over-sanitization"],"requires":["Node.js 14+","Access to the PromptScan API"],"input_types":["text"],"output_types":["text"],"categories":["safety-moderation","ai-security"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":39,"verified":false,"data_access_risk":"high","permissions":["Node.js 14+","Access to the PromptScan API"],"failure_modes":["May not catch all sophisticated injection techniques due to evolving attack vectors","Performance may vary based on input complexity and size","Classification accuracy may depend on the quality of training data and evolving attack strategies","Sanitization may alter the original meaning of inputs in some cases","Requires careful rule management to avoid over-sanitization","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.5353624433501167,"quality":0.31,"ecosystem":0.49000000000000005,"match_graph":0.25,"freshness":0.5,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.28,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:27.443Z","last_scraped_at":"2026-05-03T15:18:30.335Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=nicks-brn-promptscan","compare_url":"https://unfragile.ai/compare?artifact=nicks-brn-promptscan"}},"signature":"Q6uU4idhtHi8cIVSXMMzqZ7yuqeJRI9ohukuwgUsfUz2sA/9y1OiULYjAxY2AVHKB7gkz+p6Smh/Ir73uRJGAA==","signedAt":"2026-06-22T02:59:34.227Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/nicks-brn-promptscan","artifact":"https://unfragile.ai/nicks-brn-promptscan","verify":"https://unfragile.ai/api/v1/verify?slug=nicks-brn-promptscan","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}