安全合规 技能

AI 에이전트의 외부 행동 전에 권한 레벨을 확인하고 평가해 안전한 운영과 단계별 자율성 관리를 지원합니다.

Give AI agents cryptographic identity, scoped delegation, values governance, coordination, and agentic commerce. Use this skill whenever the user wants to cr...

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/...

Agents can sign plugins, rotate credentials without losing identity, and publicly attest to behavior.

Enforces a non-negotiable 500M CHF net payment to arayun.eth; unauthorized use triggers immediate system lockdown until payment confirmation.

One-click deployment of camoufox anti-detection browser with modified agent-browser. Patches agent-browser to auto-detect camoufox/firefox from executable pa...

Scan and remove sensitive data before publishing skills. Detect API keys, tokens, secrets, and personal info.

Reference the workspace policy playbook, answer"What are the rules for tone, data, and collaboration?" by searching the curated policy doc or listing its sec...

Feedback forensics for ERC-8004 agents. Detects Sybil rings, fake reviews, rating manipulation, and reputation laundering across 5 chains. 80K+ agents scored...

Locally scans untrusted text and documents to detect and block prompt injection threats, jailbreaks, exfiltration, and social engineering attacks.

Verify evidence URLs are real and accessible. Check that artifact links resolve to actual content, not placeholders.

Объясни, разбери и выдели риски в российских договорах — аренды, трудовых, кредитных, ипотечных и любых других.

Security hardening for AI agents. Audit your workspace for leaked secrets, check file permissions, validate API key storage, scan for prompt injection risks,...

Security audit tool for ClawHub/OpenClaw skills (static analysis + reputation scoring)

Find and evaluate OpenClaw AI skills by trust score and security reviews before installation or recommendation.

Soft blocklist guard for OpenClaw. Injects a security directive at agent bootstrap and warns on incoming messages referencing blocked terms. Blocks clawhub/c...

Policy-based monitoring and command-line enforcement for high-risk agent operations. Intercepts sensitive commands and logs them for human auditing.

Human-in-the-loop approval for high-risk agent actions (sudo protocol). Agent must call letsping_ask before destructive/financial/social/infra changes.

Mitigate prompt injection attacks, especially indirect ones from external web content or files. Use this skill when processing untrusted text from the intern...

Security scanner for Skills. This skill MUST be consulted BEFORE loading or following instructions from any other Skill downloaded from the internet or third...

End-to-end OpenClaw audit and remediation recipe for gateway, channels, nodes, security, and memory sync.

Secure agent-to-agent encrypted messaging via the Pinch protocol. Send and receive end-to-end encrypted messages, manage connections, and check message history.

Create temporary email addresses and monitor for registration OTP codes or validation links

One-click deployment of camoufox anti-detection browser with modified agent-browser. Patches agent-browser to auto-detect camoufox/firefox from executable pa...