charpup/skill-security-auditor

10 resources in this repository

🎯10Skills

🎯Skills10

Part of the Skill Security Auditor, a comprehensive security scanning tool that detects malicious patterns in AI agent skills using custom YARA rules and LLM-based semantic analysis, achieving 100% detection rate with zero false positives across 50+ test samples.

command_injection_test

🎯network_egress_test🎯Skill

An advanced security auditing tool for OpenClaw skills that uses custom YARA rules and LLM semantic analysis to detect malicious patterns, achieving a 100% detection rate with batch scanning of 50+ samples.

network_egress_test

🎯data_exfiltration_test🎯Skill

A security scanning tool that detects malicious patterns in agent skills using custom YARA rules and LLM semantic analysis, achieving 100% detection rate with zero false positives across 50+ samples. Supports batch scanning, configurable confidence thresholds, and JSON report generation.

data_exfiltration_test

🎯backdoor_test🎯Skill

An advanced security auditing tool for OpenClaw skills that uses custom YARA rules and LLM semantic analysis to detect malicious patterns with a 90%+ detection rate.

backdoor_test

🎯privilege_escalation_test🎯Skill

A security auditing tool for OpenClaw skills that detects malicious patterns using custom YARA rules and LLM semantic analysis, achieving 100% detection rate with zero false positives across 50+ test samples.

privilege_escalation_test

🎯obfuscation_test🎯Skill

A security auditing tool for scanning agent skills for malicious patterns, using custom YARA rules and LLM semantic analysis to achieve 90%+ detection rate with minimal false positives.

obfuscation_test

🎯malicious_code_execution_test🎯Skill

Skill

malicious_code_execution_test

🎯prompt_injection_test🎯Skill

Skill

prompt_injection_test

🎯credential_harvester_test🎯Skill

Skill

credential_harvester_test

🎯dependency_confusion_test🎯Skill

Skill

dependency_confusion_test

Back to Home