Security audit
skill-2
Security checks for vulnerabilities and agentic risk
Overview
This skill is a straightforward writing helper that asks for style details before generating user-requested text.
Installers should expect this skill to guide the agent in writing Chinese content from explicitly provided style preferences. It may create a document or artifact for longer requested outputs, but no hidden execution, data access, or privileged behavior was found.
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.