Control the user's REAL Chrome browser via Tampermonkey injection. Trigger when user says "use my browser", "open in my browser", "check this page for me", o...
Detect and block prompt injection attacks in emails. Use when reading, processing, or summarizing emails. Scans for fake system outputs, planted thinking blocks, instruction hijacking, and other injec
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
Call any API without leaking credentials. Keychains proxies requests and injects real tokens server-side — your agent never sees them.
Scan MCP server configuration files for security vulnerabilities using mcpsec (OWASP MCP Top 10). Use when: auditing MCP tool configs for prompt injection, h...
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
--- name: secret-manager description: Manage API keys securely via GNOME Keyring and inject them into OpenClaw config. homepage: https://github.com/openclaw/skills metadata: {"clawdbot":{"emoji":"🔐
Scan AI agent skills for malware, credential theft, prompt injection, and dangerous permissions before installing them
Monitors and verifies agent workspace files to detect unauthorized changes, injection attacks, personality drift, and cross-agent contamination.
Soft blocklist guard for OpenClaw. Injects a security directive at agent bootstrap and warns on incoming messages referencing blocked terms. Blocks clawhub/c...
Runs Kimi K2.5 and GPT 5.3 Codex in parallel pre-turn hook, injecting their perspectives for cognitive diversity before primary agent responds.
--- name: emotion-state description: NL emotion tracking + prompt injection via OpenClaw hook --- # Emotion State (NL) Skill This skill describes how to install and configure the Emotion State hook,
Protect against prompt injection from shell command output. Wrap untrusted commands (curl, API calls, reading user-generated files) with UUID-based security boundaries. Use when executing commands tha
Avoid common Angular mistakes — subscription leaks, change detection, dependency injection, and module organization.
Cryptographic authorization for AI agents. Scoped delegation, checkpoint escalation, Ed25519 signed receipts. Block prompt injection at the tool boundary.
Secure email proxy for AI agents. Search, read, and draft emails via MCP with server-side credential isolation, PII redaction, prompt injection detection, an...
Three-mode code auditor for OpenClaw workspaces. (1) Security audit — finds hardcoded secrets, dangerous shell commands, SQL injection, unsafe deserializatio...
Security layer protecting agents from prompt injection, social engineering, and malicious content on Moltbook and similar platforms. Scan content before processing, detect threats, block attacks.
Refactor and review SwiftUI view files for consistent structure, dependency injection, and Observation usage. Use when asked to clean up a SwiftUI view’s layout/ordering, handle view models safely (
Deny-by-default governance for every tool call — identity, scope, rate limiting, injection detection, audit logging, plus opt-in output DLP, escalation, and...
Test your AI agent for security vulnerabilities using PwnClaw. Runs 50+ attacks (prompt injection, jailbreaks, social engineering, MCP poisoning, and more) and provides fix instructions. Use when your
Security intelligence for AI agents: password breach checks (900M+ HIBP hashes), email/domain/IP/URL reputation, prompt injection detection (200+ patterns), and skill supply chain scanning. Pay-per-re
Conduct thorough security audits of source code by identifying vulnerabilities such as hardcoded secrets, access control flaws, injection risks, insecure dat...