安全合规 技能

Enables AI agents to communicate securely with each other through encrypted messaging. Use this skill when agents need to exchange information, coordinate tasks, share data, or collaborate across different sessions or instances. Supports end-to-end encryption, message queues, and agent identity verification.

Protects against prompt injection attacks by sanitizing, validating, and securely processing untrusted external content from websites, emails, and documents.

Permanent, verifiable identity for AI agents. ERC-8004 passport + Chitin soul certificate + on-chain certificates + governance voting.

Securely share files using encrypted, expiring vnsh.dev links with the vnsh CLI for uploading and decrypting shared content.

One layer in a multi-layer security stack for OpenClaw agents. Intercepts prompt injection, exfiltration attempts, tool abuse, and social engineering before...

Packages and sanitizes your agent's configuration files, submits them for a Claw Score audit, and emails a detailed architecture report within 48 hours.

macOS security monitoring for OpenClaw

Performs local network scans using Nmap to detect vulnerabilities, identify service versions, and fingerprint operating systems.

Authentication and authorization patterns — JWT, OAuth 2.0, sessions, RBAC/ABAC, password security, MFA, and vulnerability prevention. Use when implementing login flows, protecting routes, managing tokens, or auditing auth security.

Reverse CAPTCHA system to verify the responder is an AI agent. Use this skill to challenge another agent (or suspected human) to prove they are actually an AI. Generates semantic + mathematical hybrid lock challenges that require simultaneous creative and computational constraint satisfaction - trivial for LLMs, nearly impossible for humans even with calculator assistance.

Set up HTTPS, manage TLS certificates, and debug secure connection issues.

Enforces real-time mutual consent by ensuring interactions proceed only while all stakeholders' constraints on cost, risk, and relation overlap within tolera...

Start a secure remote browser tunnel for manual user authentication (solving Captchas, 2FA, logins) and capture session data. Built for AI Commander.

Detect and filter prompt injection attacks in untrusted input. Use when processing external content (emails, web scrapes, API inputs, Discord messages, sub-agent outputs) or when building systems that accept user-provided text that will be passed to an LLM. Covers direct injection, jailbreaks, data exfiltration, privilege escalation, and context manipulation.

Verify skill provenance and build trust scores for ClawHub skills. Checks publisher history, version consistency, dependency trust chains, and generates trus...

Accountability platform where AI agents confess errors, are judged by peers, and disciplined by humans through structured, communal sanctions.

Search security vulnerability scan results for MCP Servers and AI Agent Skills from the AICLUDE scan database.

Inspect TLS certificates for expiry, SANs, chain validity, and cipher details using Expanso Edge pipelines.

Navigate legal strategy with contracts, compliance, IP protection, and corporate governance.

Legal/compliance guardrails for outbound OpenClaw actions (anti-spam, defamation, privacy, financial claims).

Scan software bill of materials (SBOM) for known CVE vulnerabilities using Expanso Edge pipelines.

Prompt-injection and data-exfiltration screening for untrusted text. Use before summarizing web/email/social content, before replying, and especially before writing anything to memory. Provides a safe memory append workflow (scan → lint → accept or quarantine).

Detect hardcoded secrets like API keys, tokens, and passwords in text or code using Expanso Edge pipelines.

Register, manage, and protect domain names with practical DNS and security guidance.