Security audit
Skill Launch Doctor
Security checks for vulnerabilities and agentic risk
Overview
The skill bundle contains disclosed ClawHub, Convex, documentation, and review workflows with some powerful admin and production operations, but the artifacts consistently gate those actions behind user intent, authentication, dry runs, confirmation, or explicit signoff.
Install this only if you want these ClawHub/Convex maintainer workflows available to your agent. Be especially careful when invoking moderation, email, PR-commenting, proof publishing, or production migration tasks, because those can change live services or public content when run with authenticated credentials.
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.