Security audit
Markdown to Feishu Post
Security checks for vulnerabilities and agentic risk
Overview
The inspected skill content is coherent for ClawHub and Convex development workflows, with powerful actions disclosed and generally gated by user intent or existing platform controls.
Install only if you trust these skills to guide ClawHub/Convex engineering workflows. Pay particular attention to moderation commands and the autoreview helper's full-access default; use the documented confirmation steps and opt out of full-access mode when reviewing untrusted code.
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.