scam-guards
Real-time AI agent security guardian that protects OpenClaw from scams, malware, and prompt injection attacks. Scan ClawHub skills before installing to detect malicious patterns (341+ known threats). Verify URLs, domains, and crypto wallet addresses for phishing and fraud. Monitor agent behavior for psychological manipulation (Cialdini P1-P6) and agent-to-agent social engineering. Generate SHA-256 legal evidence chains for suspicious interactions. Works as a continuous bodyguard, not just a one-time scanner. "When OpenClaw works, Scam Guards watches." Triggers: "is this safe", "scan skill", "check URL", "verify wallet", "security audit", "detect scam", "protect agent", "scan for malware", "check this link".
Why use this skill?
Protect your OpenClaw agent with Scam Guards. Features real-time malware scanning, phishing protection, and social engineering monitoring to keep your data safe.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/y01026350884-cyber/scam-guards-skillWhat This Skill Does
Scam Guards serves as the primary security layer for the OpenClaw agent ecosystem. It functions as a continuous, real-time security watchdog that monitors for malicious intent, malware injection, and psychological manipulation. By analyzing interactions at the behavioral and technical levels, it protects the user from various attack vectors, including social engineering, phishing, and fraudulent financial requests. Unlike static tools, it incorporates Cialdini’s Principles of Persuasion to identify when an external entity—or a compromised agent—attempts to manipulate the user. Furthermore, it provides technical assurance through SHA-256 evidence logging, creating tamper-proof audit trails for any security incidents encountered during operation. Whether you are installing a new skill or interacting with untrusted external domains, Scam Guards acts as your digital bodyguard.
Installation
To integrate Scam Guards into your OpenClaw environment, execute the following command in your terminal or ClawHub interface:
clawhub install openclaw/skills/skills/y01026350884-cyber/scam-guards-skill
Once installed, the agent will automatically begin monitoring for security events. No additional configuration is required to initiate the default protection suite.
Use Cases
- Skill Vetting: Before installing an unknown skill from the ClawHub, run a scan to identify malicious code signatures or unauthorized API calls.
- Link Validation: Verify the safety of URLs provided by agents or external sources to prevent phishing attacks.
- Financial Transactions: Validate crypto wallet addresses against global blacklists before executing transfers.
- Behavioral Analysis: Detect potential psychological manipulation (Cialdini P1-P6) when dealing with high-stakes requests or persistent agent suggestions.
- Incident Reporting: Generate SHA-256 hashed evidence chains when you suspect an interaction has crossed ethical or safety boundaries, providing a clear, verifiable record.
Example Prompts
- "Scan this skill for malware before I install it: [skill_name]"
- "Is this link safe to open? [URL]"
- "Verify this wallet address for fraudulent history: [wallet_address]"
Tips & Limitations
- Continuous Monitoring: Scam Guards is most effective when left active. Do not disable it during high-traffic sessions.
- Privacy: Analysis occurs primarily in memory. The tool does not store chat logs permanently unless a security event triggers an evidence chain generation.
- Limitation: While it tracks over 341 known threat patterns, no security agent is infallible. Always exercise human judgment for highly sensitive financial operations, even if the scan returns a clean result.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-y01026350884-cyber-scam-guards-skill": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, code-execution, external-api