Security audit
文曲·发布
Security checks for vulnerabilities and agentic risk
Overview
This skill prepares local publish-ready copies of drafts and does not show hidden execution, credential use, or automatic online publishing.
Installers should expect this skill to read article drafts and wenqu metadata, create local publish folders, and optionally call wenqu-image for cover art. Review the separate wenqu-image skill before using cover generation, and note that this skill says online platform publishing is only a future placeholder and should not happen automatically.
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.