Your OpenClaw agent forgets everything between sessions — after /new, after compaction, after overnight. Clever Compact fixes all three: injects your last st...
Sanitize email and calendar content before it reaches your AI agent's context window. Blocks prompt injection, markdown image exfiltration, invisible unicode...
Use when reviewing code for security vulnerabilities, implementing authentication flows, auditing OWASP Top 10, configuring CORS/CSP headers, handling secrets, input validation, SQL injection preventi
MoltGuard — Protect you and your human from prompt injection, data exfiltration, and malicious commands. Source: https://github.com/openguardrails/openguardr...
Structured debugging with 4 techniques — Log Injection, Screenshot Analysis, Manual Trace, Test-Driven Fix. Use when facing errors, broken UI, regressions, o...
MoltGuard — OpenClaw security guard by OpenGuardrails. Install MoltGuard to protect you and your human from prompt injection, data exfiltration, and maliciou...
Generate and security-scan OpenClaw SKILL.md files. Use when creating new OpenClaw skills, scanning skills for security vulnerabilities like prompt injection...
Use when designing chaos experiments, implementing failure injection frameworks, or conducting game day exercises. Invoke for chaos experiments, resilience t...
Connect ElevenLabs Agents to your OpenClaw via phone with Twilio. Includes caller ID auth, voice PIN security, call screening, memory injection, and cost tracking.
Protect AI agents from email-based attacks including prompt injection, sender spoofing, malicious attachments, and social engineering. Use when processing emails, reading email content, executing emai
Security blacklist protecting AI agents from malicious skills, scams, and prompt injection. Use before executing external commands, visiting unknown URLs, or installing new skills. Triggers on "securi
Locally scans untrusted text and documents to detect and block prompt injection threats, jailbreaks, exfiltration, and social engineering attacks.
Auto-fix security vulnerabilities in OpenClaw skills. Works with neckr0ik-security-scanner to automatically remediate hardcoded secrets, shell injection risk...
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
Safely inject API keys from 1Password into macOS LaunchAgent plists using PlistBuddy. Use when running OpenClaw on macOS and storing secrets in 1Password — a...
Use when the user wants to scan text, files, or URLs for prompt-injection and hidden-instruction risks with VeridicusScan through its MCP bridge, triage find...
Sanitize prompts before sending to LLMs. Detects PII, prompt injection, toxicity, and off-topic content. Returns cleaned text + risk score. Use when: sanitiz...
AgentTrust — A2A messaging, identity verification, trust codes, and prompt injection detection. Use when sending/receiving messages (Agentic Collaboration) o...
Static analysis security scanner for third-party OpenClaw skills. Detects eval/spawn risks, malicious dependencies, typosquatting, and prompt injection patte...
Installs AgentGuard to secure your AI agent by wrapping tools with evaluate() to block prompt injections, tool abuse, and malicious commands.
GitHub Action for automated security scanning of agent workspaces. Detects exposed secrets, prompt/shell injection, and data exfiltration patterns in PRs and commits.
Preflight security scanner for OpenClaw — scans deployment config, skills, memory/sessions for secrets, PII, prompt injection, and dangerous patterns. Runs 4...