Security audit
文献助手
Security checks for vulnerabilities and agentic risk
Overview
This appears to be a coherent ClawHub maintainer skill bundle, but it includes powerful disclosed workflows that can run full-access review agents, publish PR artifacts, and perform staff moderation actions.
Install only in a ClawHub maintainer environment where you expect staff moderation, GitHub PR publishing, Convex deployment, and local review automation. Review the autoreview full-access default before use, prefer its no-yolo mode when possible, and ensure moderation commands are run only with explicit targets, reasons, confirmation, and an account whose permissions you intend to use.
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.