Security audit
Zhiqiu
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed industry-analysis workflow that uses public research data and optional report-fetching support without hidden persistence or destructive behavior.
Before installing, note that the skill may perform web research and can optionally use a third-party financial-report-fetching skill. Review that dependency if you enable it, and expect generated reports to cite fresh public sources rather than rely on cached knowledge.
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.