Security audit
基金投顾
Security checks for vulnerabilities and agentic risk
Overview
This skill coherently sets up and runs Cue fund-advisory research with disclosed network use, credit consumption, and local Cue credentials.
Before installing, confirm you are comfortable with the skill using Cue's online service, reading your local Cue API key through the runner, potentially cloning/updating the Cue runner repository, and spending Cue credits only after your explicit approval.
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.