Security Center
Transparency reports, alerts, and how we keep your agent safe
Recent Security Alerts
Suspicious API call pattern detected
A skill batch was flagged for unexpected outbound requests to unlisted domains. Affected skills temporarily suspended pending review.
Prompt injection attempt in community skill
A newly submitted skill contained crafted instructions designed to override system prompts. Skill blocked and author notified.
Updated scanning engine v2.2.0 deployed
Improved detection accuracy for data exfiltration patterns. All existing skills re-scanned with the new engine.
Our 10-Point Security Scan
Every skill is automatically analyzed against these criteria using our AI scanning engine.
Prompt Injection Detection
HighChecks for malicious prompt override attempts in skill instructions
Data Exfiltration Risk
CriticalDetects patterns that may expose sensitive user data to external services
Unauthorized API Calls
HighFlags unexpected external API calls not documented in the skill
File System Access
MediumReviews file read/write patterns for potential data theft
Credential Harvesting
CriticalDetects attempts to collect API keys or authentication tokens
Code Execution Risk
HighEvaluates dynamic code execution patterns for sandbox escapes
Network Request Analysis
MediumInspects all outbound network calls for suspicious destinations
Social Engineering Patterns
MediumIdentifies manipulation attempts targeting end users
Permission Scope Creep
MediumChecks if skill requests more permissions than documented
Supply Chain Integrity
HighVerifies dependency sources and checks for known vulnerabilities
🔍 Recently Audited Skills
Security Auditor
Use when reviewing code for security vulnerabilities, implem
Security Audit Toolkit
Audit codebases and infrastructure for security issues. Use
security-reviewer
Use when conducting security audits, reviewing code for vuln
Openclaw Security Audit
Audit OpenClaw/Clawdbot deployments for misconfigurations an
Openclaw Safety Coach
Safety coach for OpenClaw users. Refuses harmful, illegal, o
Security code review
Conduct thorough security audits of source code by identifyi
Report a Security Issue
Found a skill that looks suspicious? Help keep the community safe by reporting it. All reports are reviewed by our security team within 24 hours.