Security audit
Docx Tool
Security checks for vulnerabilities and agentic risk
Overview
The reviewed skill artifacts are coherent with their stated developer-workflow purposes and disclose their sensitive actions, though some workflows require care because they can run commands, publish proof artifacts, or perform staff moderation actions.
Install only if you want these ClawHub/Convex maintenance workflows. Read the moderation and autoreview sections before use: moderation can ban or restore accounts and alter public skill visibility, while autoreview may run a nested reviewer with broad local access unless you opt out with the documented no-yolo setting. Use dry-run/confirmation paths for publishing proof or migration work.
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.