{ "schemaVersion": "1.0", "item": { "slug": "shieldcortex-skill", "name": "Shieldcortex Skill", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/jarvis-drakon/shieldcortex-skill", "canonicalUrl": "https://clawhub.ai/jarvis-drakon/shieldcortex-skill", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/shieldcortex-skill", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=shieldcortex-skill", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/shieldcortex-skill" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/shieldcortex-skill", "agentPageUrl": "https://openagent3.xyz/skills/shieldcortex-skill/agent", "manifestUrl": "https://openagent3.xyz/skills/shieldcortex-skill/agent.json", "briefUrl": "https://openagent3.xyz/skills/shieldcortex-skill/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "ShieldCortex — Persistent Memory & Security for AI Agents", "body": "Give your AI agent a brain that persists between sessions — and protect it from memory poisoning attacks." }, { "title": "Description", "body": "ShieldCortex is a complete memory system with built-in security. It gives AI agents persistent, intelligent memory with semantic search, knowledge graphs, decay-based forgetting, and contradiction detection. Every memory write passes through a 6-layer defence pipeline that blocks prompt injection, credential leaks, and poisoning attacks.\n\nUse when:\n\nYou want your agent to remember things between sessions (decisions, preferences, architecture, context)\nYou need semantic search across past memories (not just keyword matching)\nYou want automatic memory consolidation, decay, and cleanup\nYou want knowledge graph extraction from memories (entities, relationships)\nYou need to protect memory from prompt injection or poisoning attacks\nYou want credential leak detection in memory writes\nYou want to audit what's been stored in and retrieved from memory\nYou want to scan agent instruction files (SKILL.md, .cursorrules, CLAUDE.md) for hidden threats\n\nDo NOT use when:\n\nYou only need simple key-value storage (use a config file)\nYou want ephemeral session-only context (use the agent's built-in context window)\nYou need a vector database for RAG pipelines (ShieldCortex is agent memory, not document retrieval)" }, { "title": "Prerequisites", "body": "Node.js >= 18\nnpm or pnpm" }, { "title": "Install", "body": "npm install -g shieldcortex\n\nFor OpenClaw integration (installs the cortex-memory hook):\n\nshieldcortex openclaw install\n\nFor Claude Code / VS Code / Cursor MCP integration:\n\nshieldcortex install" }, { "title": "As an OpenClaw hook (automatic)", "body": "After shieldcortex openclaw install, the hook activates on next restart:\n\nAuto-saves important session context on compaction\nInjects relevant past memories on session start\n\"remember this: ...\" keyword trigger saves memories inline" }, { "title": "CLI Commands", "body": "# Check status\nshieldcortex status\n\n# Scan content for threats\nshieldcortex scan \"some text to check\"\n\n# Full security audit of your agent environment\nshieldcortex audit\n\n# Scan all installed skills/instruction files for hidden threats\nshieldcortex scan-skills\n\n# Scan a single skill file\nshieldcortex scan-skill ./path/to/SKILL.md\n\n# Build knowledge graph from existing memories\nshieldcortex graph backfill\n\n# Start the visual dashboard\nshieldcortex --dashboard" }, { "title": "As a Library (programmatic)", "body": "import {\n addMemory,\n getMemoryById,\n runDefencePipeline,\n scanSkill,\n extractFromMemory,\n consolidate,\n initDatabase\n} from 'shieldcortex';\n\n// Initialize\ninitDatabase('/path/to/memories.db');\n\n// Add a memory (automatically passes through defence pipeline)\naddMemory({\n title: 'API uses OAuth2',\n content: 'The payment API requires OAuth2 bearer tokens, not API keys',\n category: 'architecture',\n importance: 'high',\n project: 'my-project'\n});\n\n// Scan content before processing\nconst result = runDefencePipeline(untrustedContent, 'Email Import', {\n type: 'external',\n identifier: 'email-scanner'\n});\n\nif (result.allowed) {\n // Safe to process\n}\n\n// Extract knowledge graph entities\nconst { entities, triples } = extractFromMemory(\n 'Database Migration',\n 'We switched from MySQL to PostgreSQL for the auth service',\n 'architecture'\n);\n// entities: [{name: 'MySQL', type: 'service'}, {name: 'PostgreSQL', type: 'service'}, ...]\n// triples: [{subject: 'auth service', predicate: 'uses', object: 'PostgreSQL'}, ...]" }, { "title": "Memory System Features", "body": "FeatureDescriptionPersistent StorageSQLite-backed, survives restarts and compactionSemantic SearchFind memories by meaning, not just keywordsProject ScopingIsolate memories per project/workspaceImportance LevelsCritical, high, normal, low with auto-decayCategoriesArchitecture, decisions, preferences, context, learnings, errorsDecay & ForgettingOld, unaccessed memories fade — like a real brainConsolidationAutomatic merging of similar/duplicate memoriesContradiction DetectionFlags when new memories conflict with existing onesKnowledge GraphExtracts entities and relationships from memoriesActivation ScoringRecently accessed memories get retrieval prioritySalience ScoringImportant memories surface first in search" }, { "title": "Security Features", "body": "LayerProtectionInput SanitisationStrip control characters, null bytes, dangerous formattingPattern DetectionRegex matching for known injection patternsAnomaly ScoringEntropy analysis, behavioural deviation detectionCredential Leak DetectionBlocks API keys, tokens, private keys (25+ patterns, 11 providers)Trust ScoringSource-based reliability scoring for memory writesAudit TrailFull forensic log of every memory operationSkill ScannerDetect prompt injection in SKILL.md, .cursorrules, CLAUDE.md" }, { "title": "ShieldCortex Cloud (Optional)", "body": "Sync audit data to a team dashboard for cross-project visibility:\n\nshieldcortex config set-api-key \n\nFree local package is unlimited. Cloud adds team dashboards, audit aggregation, and alerts." }, { "title": "Links", "body": "npm: https://www.npmjs.com/package/shieldcortex\nGitHub: https://github.com/Drakon-Systems-Ltd/ShieldCortex\nWebsite: https://shieldcortex.ai\nDocs: https://github.com/Drakon-Systems-Ltd/ShieldCortex#readme" }, { "title": "70 Exported APIs", "body": "The library exports 70 named functions and types covering defence, memory, knowledge graph, skill scanning, and audit. Full list in the CHANGELOG." } ], "body": "ShieldCortex — Persistent Memory & Security for AI Agents\n\nGive your AI agent a brain that persists between sessions — and protect it from memory poisoning attacks.\n\nDescription\n\nShieldCortex is a complete memory system with built-in security. It gives AI agents persistent, intelligent memory with semantic search, knowledge graphs, decay-based forgetting, and contradiction detection. Every memory write passes through a 6-layer defence pipeline that blocks prompt injection, credential leaks, and poisoning attacks.\n\nUse when:\n\nYou want your agent to remember things between sessions (decisions, preferences, architecture, context)\nYou need semantic search across past memories (not just keyword matching)\nYou want automatic memory consolidation, decay, and cleanup\nYou want knowledge graph extraction from memories (entities, relationships)\nYou need to protect memory from prompt injection or poisoning attacks\nYou want credential leak detection in memory writes\nYou want to audit what's been stored in and retrieved from memory\nYou want to scan agent instruction files (SKILL.md, .cursorrules, CLAUDE.md) for hidden threats\n\nDo NOT use when:\n\nYou only need simple key-value storage (use a config file)\nYou want ephemeral session-only context (use the agent's built-in context window)\nYou need a vector database for RAG pipelines (ShieldCortex is agent memory, not document retrieval)\nPrerequisites\nNode.js >= 18\nnpm or pnpm\nInstall\nnpm install -g shieldcortex\n\n\nFor OpenClaw integration (installs the cortex-memory hook):\n\nshieldcortex openclaw install\n\n\nFor Claude Code / VS Code / Cursor MCP integration:\n\nshieldcortex install\n\nQuick Start\nAs an OpenClaw hook (automatic)\n\nAfter shieldcortex openclaw install, the hook activates on next restart:\n\nAuto-saves important session context on compaction\nInjects relevant past memories on session start\n\"remember this: ...\" keyword trigger saves memories inline\nCLI Commands\n# Check status\nshieldcortex status\n\n# Scan content for threats\nshieldcortex scan \"some text to check\"\n\n# Full security audit of your agent environment\nshieldcortex audit\n\n# Scan all installed skills/instruction files for hidden threats\nshieldcortex scan-skills\n\n# Scan a single skill file\nshieldcortex scan-skill ./path/to/SKILL.md\n\n# Build knowledge graph from existing memories\nshieldcortex graph backfill\n\n# Start the visual dashboard\nshieldcortex --dashboard\n\nAs a Library (programmatic)\nimport {\n addMemory,\n getMemoryById,\n runDefencePipeline,\n scanSkill,\n extractFromMemory,\n consolidate,\n initDatabase\n} from 'shieldcortex';\n\n// Initialize\ninitDatabase('/path/to/memories.db');\n\n// Add a memory (automatically passes through defence pipeline)\naddMemory({\n title: 'API uses OAuth2',\n content: 'The payment API requires OAuth2 bearer tokens, not API keys',\n category: 'architecture',\n importance: 'high',\n project: 'my-project'\n});\n\n// Scan content before processing\nconst result = runDefencePipeline(untrustedContent, 'Email Import', {\n type: 'external',\n identifier: 'email-scanner'\n});\n\nif (result.allowed) {\n // Safe to process\n}\n\n// Extract knowledge graph entities\nconst { entities, triples } = extractFromMemory(\n 'Database Migration',\n 'We switched from MySQL to PostgreSQL for the auth service',\n 'architecture'\n);\n// entities: [{name: 'MySQL', type: 'service'}, {name: 'PostgreSQL', type: 'service'}, ...]\n// triples: [{subject: 'auth service', predicate: 'uses', object: 'PostgreSQL'}, ...]\n\nMemory System Features\nFeature\tDescription\nPersistent Storage\tSQLite-backed, survives restarts and compaction\nSemantic Search\tFind memories by meaning, not just keywords\nProject Scoping\tIsolate memories per project/workspace\nImportance Levels\tCritical, high, normal, low with auto-decay\nCategories\tArchitecture, decisions, preferences, context, learnings, errors\nDecay & Forgetting\tOld, unaccessed memories fade — like a real brain\nConsolidation\tAutomatic merging of similar/duplicate memories\nContradiction Detection\tFlags when new memories conflict with existing ones\nKnowledge Graph\tExtracts entities and relationships from memories\nActivation Scoring\tRecently accessed memories get retrieval priority\nSalience Scoring\tImportant memories surface first in search\nSecurity Features\nLayer\tProtection\nInput Sanitisation\tStrip control characters, null bytes, dangerous formatting\nPattern Detection\tRegex matching for known injection patterns\nAnomaly Scoring\tEntropy analysis, behavioural deviation detection\nCredential Leak Detection\tBlocks API keys, tokens, private keys (25+ patterns, 11 providers)\nTrust Scoring\tSource-based reliability scoring for memory writes\nAudit Trail\tFull forensic log of every memory operation\nSkill Scanner\tDetect prompt injection in SKILL.md, .cursorrules, CLAUDE.md\nShieldCortex Cloud (Optional)\n\nSync audit data to a team dashboard for cross-project visibility:\n\nshieldcortex config set-api-key \n\n\nFree local package is unlimited. Cloud adds team dashboards, audit aggregation, and alerts.\n\nLinks\nnpm: https://www.npmjs.com/package/shieldcortex\nGitHub: https://github.com/Drakon-Systems-Ltd/ShieldCortex\nWebsite: https://shieldcortex.ai\nDocs: https://github.com/Drakon-Systems-Ltd/ShieldCortex#readme\n70 Exported APIs\n\nThe library exports 70 named functions and types covering defence, memory, knowledge graph, skill scanning, and audit. Full list in the CHANGELOG." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/jarvis-drakon/shieldcortex-skill", "publisherUrl": "https://clawhub.ai/jarvis-drakon/shieldcortex-skill", "owner": "jarvis-drakon", "version": "2.10.5", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/shieldcortex-skill", "downloadUrl": "https://openagent3.xyz/downloads/shieldcortex-skill", "agentUrl": "https://openagent3.xyz/skills/shieldcortex-skill/agent", "manifestUrl": "https://openagent3.xyz/skills/shieldcortex-skill/agent.json", "briefUrl": "https://openagent3.xyz/skills/shieldcortex-skill/agent.md" } }