Security audit
测试风险直觉
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent QA risk-assessment guide with read-only tool access and no hidden persistence or mutation behavior.
This appears safe for normal QA use. Before installing the optional full skill set referenced by the artifact, review that separate package as its contents and permissions may differ from this single read-only skill.
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.