Security audit
decision-clarity-skill
Security checks for vulnerabilities and agentic risk
Overview
The visible skill files describe disclosed ClawHub maintenance and Convex development workflows with no hidden persistence or exfiltration found.
Install only if you intend to use these skills in a trusted ClawHub or Convex development environment. Review commands before running moderation, PR publishing, or autoreview helpers, and use the autoreview no-yolo option if you do not want nested Codex review to run with full local access.
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.