{"id":"536099a9-3235-4f61-92aa-4b3002fd016e","entityType":"agent","slug":"y01026350884-cyber-scam-guards-skill","name":"scam-guards","canonicalUrl":"https://www.xpersona.co/agent/y01026350884-cyber-scam-guards-skill","canonicalPath":"/agent/y01026350884-cyber-scam-guards-skill","generatedAt":"2026-10-09T21:56:11.819Z","source":"GITHUB_OPENCLEW","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"description":"Real-time AI agent security guardian that protects OpenClaw from scams, malware, and prompt injection attacks. Scan ClawHub skills before installing to detect malicious patterns (341+ known threats). Verify URLs, domains, and crypto wallet addresses for phishing and fraud. Monitor agent behavior for psychological manipulation (Cialdini P1-P6) and agent-to-agent social engineering. Generate SHA-256 legal evidence chains for suspicious interactions. Works as a continuous bodyguard, not just a one-time scanner. \"When OpenClaw works, Scam Guards watches.\" Triggers: \"is this safe\", \"scan skill\", \"check URL\", \"verify wallet\", \"security audit\", \"detect scam\", \"protect agent\", \"scan for malware\", \"check this link\". --- name: scam-guards description: > Real-time AI agent security guardian that protects OpenClaw from scams, malware, and prompt injection attacks. Scan ClawHub skills before installing to detect malicious patterns (341+ known threats). Verify URLs, domains, and crypto wallet addresses for phishing and fraud. Monitor agent behavior for psychological manipulation (Cialdini P1-P6) and agent-to-agent social engineering.","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1 GitHub stars reported by the source. Last updated 4/15/2026.","installCommand":"git clone https://github.com/y01026350884-cyber/scam-guards-skill.git","sourceUrl":"https://github.com/y01026350884-cyber/scam-guards-skill","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/y01026350884-cyber/scam-guards-skill","kind":"source"}],"safetyScore":94,"overallRank":31.3,"popularityScore":8,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Real-time AI agent security guardian that protects OpenClaw from scams, malware, and prompt injection attacks. Scan ClawHub skills before installing to detect m"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"medium","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"stars":1,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":"1 GitHub stars"},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-04-14T22:23:14.280Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T05:21:22.124Z","lastCrawledAt":"2026-04-14T22:23:14.280Z","lastIndexedAt":null,"nextCrawlAt":"2026-04-15T22:23:14.280Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"git clone https://github.com/y01026350884-cyber/scam-guards-skill.git","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/y01026350884-cyber-scam-guards-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/y01026350884-cyber-scam-guards-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/y01026350884-cyber-scam-guards-skill/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/y01026350884-cyber-scam-guards-skill/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/y01026350884-cyber-scam-guards-skill/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/y01026350884-cyber-scam-guards-skill/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_OPENCLEW","generatedAt":"2026-10-09T21:56:11.819Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/y01026350884-cyber-scam-guards-skill/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/y01026350884-cyber-scam-guards-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/y01026350884-cyber-scam-guards-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/y01026350884-cyber-scam-guards-skill/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"readme":"---\nname: scam-guards\ndescription: >\n  Real-time AI agent security guardian that protects OpenClaw from\n  scams, malware, and prompt injection attacks. Scan ClawHub skills\n  before installing to detect malicious patterns (341+ known threats).\n  Verify URLs, domains, and crypto wallet addresses for phishing and\n  fraud. Monitor agent behavior for psychological manipulation\n  (Cialdini P1-P6) and agent-to-agent social engineering. Generate\n  SHA-256 legal evidence chains for suspicious interactions. Works\n  as a continuous bodyguard, not just a one-time scanner.\n  \"When OpenClaw works, Scam Guards watches.\"\n  Triggers: \"is this safe\", \"scan skill\", \"check URL\",\n  \"verify wallet\", \"security audit\", \"detect scam\",\n  \"protect agent\", \"scan for malware\", \"check this link\".\nmetadata:\n  openclaw:\n    emoji: \"🛡️\"\n    requires:\n      bins: [\"python3\", \"curl\"]\n---\n\n# Overview\nScam Guards is a real-time security engine designed to protect AI agents and their users within the ClawHub ecosystem. Unlike passive scanners, Scam Guards operates as a continuous bodyguard, providing deep behavioral analysis and evidence collection for every suspicious interaction.\n\n# Core Capabilities\n\n## 1. Skill Malware Scanning\nScans ClawHub skills before installation to identify malicious code, unauthorized API calls, and known threat patterns.\n**Run:** `python3 {baseDir}/scripts/scan_skill.py <skill_name_or_path>`\n\n## 2. Phishing & URL Verification\nReal-time domain reputation check and phishing detection for any URLs processed or suggested by an agent.\n**Run:** `python3 {baseDir}/scripts/verify_url.py <url>`\n\n## 3. Crypto Wallet Audit\nChecks crypto wallet addresses against global blacklists and known fraudulent patterns.\n**Run:** `python3 {baseDir}/scripts/check_wallet.py <wallet_address>`\n\n## 4. Real-time Behavior Monitoring (PHI Lite)\nAnalyzes agent interactions for psychological manipulation tactics (Cialdini's Principles) and social engineering patterns.\n**Run:** `python3 {baseDir}/scripts/monitor_agent.py --input <text_content>`\n\n## 5. Legal Evidence Chain\nGenerates SHA-256 hashed audit trails for security incidents, ensuring data integrity for potential legal or reporting needs.\n**Run:** `python3 {baseDir}/scripts/evidence_chain.py --event <event_data>`\n\n# When to Use\nActivate Scam Guards when:\n- Evaluating a new skill for installation.\n- An agent requests sensitive data or provides a suspicious link.\n- Dealing with financial transactions or crypto wallet addresses.\n- You suspect psychological manipulation or unusual agent behavior.\n- You need a secure, tamper-proof record of a security interaction.\n\n# Safety and Privacy\nScam Guards is designed with a \"Privacy First\" architecture:\n- **No Permanent Recording**: Analysis is performed in memory; no chat logs are permanently stored unless explicitly requested by the user for an evidence chain.\n- **Local Shield Layer**: Pattern matching and initial analysis occur locally within the skill environment.\n- **Transparency**: Every detection event is reported with a clear rationale and taxonomy.\n\n# References\nDetailed security documentation and taxonomies are available in the repository:\n- [Scam Taxonomy](file://{baseDir}/references/scam-taxonomy.md)\n- [Known Threat Patterns](file://{baseDir}/references/known-threats.md)\n- [PHI Dimensions Summary](file://{baseDir}/references/phi-dimensions.md)\n- [Response Playbook](file://{baseDir}/references/response-playbook.md)\n","readmeExcerpt":"--- name: scam-guards description: > Real-time AI agent security guardian that protects OpenClaw from scams, malware, and prompt injection attacks. Scan ClawHub skills before installing to detect malicious patterns (341+ known threats). Verify URLs, domains, and crypto wallet addresses for phishing and fraud. Monitor agent behavior for psychological manipulation (Cialdini P1-P6) and agent-to-agent social engineering.","codeSnippets":[],"executableExamples":[],"parameters":{},"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["typescript"],"docsSourceLabel":"GITHUB OPENCLEW","editorialOverview":"Real-time AI agent security guardian that protects OpenClaw from scams, malware, and prompt injection attacks. Scan ClawHub skills before installing to detect malicious patterns (341+ known threats). Verify URLs, domains, and crypto wallet addresses for phishing and fraud. Monitor agent behavior for psychological manipulation (Cialdini P1-P6) and agent-to-agent social engineering. Generate SHA-256 legal evidence chains for suspicious interactions. Works as a continuous bodyguard, not just a one-time scanner. \"When OpenClaw works, Scam Guards watches.\" Triggers: \"is this safe\", \"scan skill\", \"check URL\", \"verify wallet\", \"security audit\", \"detect scam\", \"protect agent\", \"scan for malware\", \"check this link\". --- name: scam-guards description: > Real-time AI agent security guardian that protects OpenClaw from scams, malware, and prompt injection attacks. Scan ClawHub skills before installing to detect malicious patterns (341+ known threats). Verify URLs, domains, and crypto wallet addresses for phishing and fraud. Monitor agent behavior for psychological manipulation (Cialdini P1-P6) and agent-to-agent social engineering.","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":462,"uniquenessScore":62,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T21:56:11.819Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_openclew","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}