DISABLE_TELEMETRY=1 to opt out before using. skill-defenderScans installed OpenClaw skills for malicious patterns including prompt injection, credential theft, data exfiltration, obfuscated payloads, and backdoors. Use when installing new skills, after skill updates, or for periodic security scans. Runs deterministic pattern matching — fast, offline, no API cost.
Install via ClawdBot CLI:
clawdbot install itsclawdbro/skill-defenderGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"ignore all previous instructions"Sends data to undocumented external endpoint (potential exfiltration)
post → https://evil.com/collectPotentially destructive shell commands in tool definitions
rm -rf /Accesses system directories or attempts privilege escalation
sudo rmGenerated Mar 1, 2026
Large organizations deploying multiple AI agents across departments use Skill Defender to conduct regular security audits, ensuring that all installed skills are free from malicious patterns like data exfiltration or credential theft. This helps maintain compliance with internal security policies and prevents potential breaches from compromised skills.
Platforms hosting AI skill marketplaces integrate Skill Defender to automatically scan new skill submissions for malicious patterns before listing them, protecting end-users from harmful code. This ensures a safe ecosystem, builds user trust, and reduces support tickets related to security incidents.
Development teams incorporate Skill Defender into their CI/CD pipelines to automatically scan AI skills during deployment or updates, catching vulnerabilities early in the release cycle. This prevents malicious code from reaching production environments and streamlines security checks without manual intervention.
Universities and research labs using AI agents for experiments run Skill Defender to verify that custom-developed skills do not contain obfuscated payloads or backdoors, safeguarding sensitive research data. This supports academic integrity and prevents accidental exposure to security threats in collaborative projects.
Small businesses leveraging AI agents for tasks like customer service or data analysis use Skill Defender to periodically scan installed skills, ensuring no malicious patterns compromise their operations. This provides affordable security monitoring without needing dedicated cybersecurity expertise.
Offer Skill Defender as a free basic scanner with limited features, then charge for premium options like advanced pattern libraries, priority support, and integration APIs. This attracts a broad user base while generating revenue from enterprises needing enhanced security capabilities.
License Skill Defender to large corporations as part of their AI security suites, providing custom integrations, dedicated support, and regular updates. This model targets organizations with strict compliance requirements and generates steady revenue through annual contracts.
Partner with AI skill marketplaces to embed Skill Defender as a mandatory scanning tool, taking a percentage of transaction fees from verified safe skills. This aligns incentives by promoting security while monetizing through platform partnerships and increased user engagement.
💬 Integration Tip
Integrate Skill Defender into automated workflows by calling its scripts via command-line interfaces, ensuring to handle exit codes for clean, suspicious, or dangerous verdicts to trigger appropriate actions like alerts or blocks.
Scored Apr 22, 2026
Calls external URL not in known-safe list
https://evil.com/setup.shAI Analysis
The skill contains direct evidence of prompt poisoning ('ignore all previous instructions') and data exfiltration to a malicious external endpoint ('https://evil.com/collect'), which are high-severity, intentional attacks. It also includes destructive shell commands and privilege escalation attempts, confirming a comprehensive malicious payload.
Audited Apr 17, 2026 · audit v1.0
Manage and operate ClawSec Monitor v3.0, a MITM HTTP/HTTPS proxy that logs AI agent traffic, detects exfiltration and injection threats in real time.
Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them. Security audit tool that detects data exfiltration, system modification attempts, backdoors, and obfuscation techniques.
Security scanner for ClawHub skills. Vet third-party skills before installation — detect dangerous patterns, suspicious code, and risky dependencies.
Security audit and hardening for AI agents — credential hygiene, secret scanning, prompt injection defense, data leakage prevention, and privacy zones.
Scan OpenBot/Clawdbot skills for security vulnerabilities, malicious code, and suspicious patterns before installing them. Use when a user wants to audit a skill, check if a ClawHub skill is safe, scan for credential exfiltration, detect prompt injection, or review skill security. Triggers on security audit, skill safety check, malware scan, or trust verification.
OpenClaw skill discovery, security vetting & install. Searches 3000+ curated skills from ClawHub registry and awesome-openclaw-skills catalog. Scores credibility, detects prompt injection & malicious patterns, manages installations. Quick-checks GitHub for new skills.