# Send AgentGuard by Nano to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "nano-agentguard", "name": "AgentGuard by Nano", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/sendwealth/nano-agentguard", "canonicalUrl": "https://clawhub.ai/sendwealth/nano-agentguard", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/nano-agentguard", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=nano-agentguard", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "CLAWHUB.md", "README-GITHUB.md", "README.md", "SKILL.md", "TEST-REPORT.md", "docs/1PASSWORD-COMPARISON.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "nano-agentguard", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T13:55:35.994Z", "expiresAt": "2026-05-06T13:55:35.994Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=nano-agentguard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=nano-agentguard", "contentDisposition": "attachment; filename=\"nano-agentguard-0.4.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "nano-agentguard" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/nano-agentguard" }, "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." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/nano-agentguard", "downloadUrl": "https://openagent3.xyz/downloads/nano-agentguard", "agentUrl": "https://openagent3.xyz/skills/nano-agentguard/agent", "manifestUrl": "https://openagent3.xyz/skills/nano-agentguard/agent.json", "briefUrl": "https://openagent3.xyz/skills/nano-agentguard/agent.md" } } ``` ## Documentation ### Overview AgentGuard is a trust middleware for Phase 1 hybrid authentication: Credential Vault: Encrypted storage for API keys and OAuth tokens Permission Scopes: Define what operations need human approval Human Gate: Push confirmation requests for high-risk operations Audit Trail: Cryptographically signed operation logs Agent Registry: Track agents with credentials and permissions ### Installation # Install globally npm install -g agentguard # Or use as OpenClaw skill cp -r . ~/.openclaw/skills/agentguard ### Quick Start # Initialize vault agentguard init # Register an agent agentguard register my-agent --owner "user@example.com" # Store a credential agentguard vault store my-agent OPENAI_API_KEY sk-xxx # Define permission scope agentguard scope set my-agent --level read --dangerous require-approval # List agents agentguard list # Audit log agentguard audit my-agent --last 24h ### Permission Levels LevelAuto-approveRequires Humanread✅ Read operations❌write✅ Read/Write❌admin✅ Most operations⚠️ Dangerous onlydangerous❌ All operations✅ Always ### Dangerous Operations (Require Human Approval) Send messages/emails Financial transactions Delete data Modify system config Access sensitive credentials External API calls (configurable) ### Human Gate Integration When an agent attempts a dangerous operation: AgentGuard blocks the operation Pushes notification to owner (Feishu/Telegram/Email) Owner approves/denies with biometric confirmation If approved, operation proceeds with short-lived token All logged with cryptographic signature ### Configuration ~/.agentguard/config.json: { "vault": { "encryption": "aes-256-gcm", "keyDerivation": "pbkdf2" }, "humanGate": { "timeout": 300, "channels": ["feishu", "telegram"], "biometric": true }, "audit": { "retention": "30d", "signLogs": true } } ### API Usage (for skills) const agentguard = require('agentguard'); // Check permission const allowed = await agentguard.check('my-agent', 'send_email'); if (!allowed) { // Request human approval const approval = await agentguard.requestApproval({ agent: 'my-agent', action: 'send_email', details: { to: 'user@example.com', subject: 'Test' } }); } // Get credential const apiKey = await agentguard.getCredential('my-agent', 'OPENAI_API_KEY'); // Log action await agentguard.audit('my-agent', 'api_call', { endpoint: '/completions' }); ### Security Model Vault Encryption: AES-256-GCM with key derived from master password Credential Isolation: Each agent has separate encrypted container Audit Integrity: SHA-256 hash chain for tamper detection Human Gate: Out-of-band confirmation via trusted channel Token Expiry: Short-lived tokens (default 5 min) ### Files ~/.agentguard/ - Data directory ~/.agentguard/vault/ - Encrypted credentials ~/.agentguard/registry.json - Agent registry ~/.agentguard/audit/ - Audit logs ~/.agentguard/config.json - Configuration ### OpenClaw Integration AgentGuard integrates with OpenClaw as a skill: Add to ~/.openclaw/skills/agentguard/ Configure in workspace AGENTS.md: ## AgentGuard All external API calls require AgentGuard permission check. Dangerous operations require human approval. Use in other skills: const guard = require('agentguard'); await guard.checkOrApprove(agentId, operation, details); ### Roadmap Phase 1: CLI + Vault + Permission Scopes Phase 2: Human Gate (Feishu/Telegram integration) Phase 3: Audit Trail + Export Phase 4: OAuth2 Token Auto-refresh Phase 5: Multi-tenant Support Phase 6: DID Preparation (future Phase 2) Building trust infrastructure for the Agentic Era. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: sendwealth - Version: 0.4.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-29T13:55:35.994Z - Expires at: 2026-05-06T13:55:35.994Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/nano-agentguard) - [Send to Agent page](https://openagent3.xyz/skills/nano-agentguard/agent) - [JSON manifest](https://openagent3.xyz/skills/nano-agentguard/agent.json) - [Markdown brief](https://openagent3.xyz/skills/nano-agentguard/agent.md) - [Download page](https://openagent3.xyz/downloads/nano-agentguard)