Security audit
Skill Publisher Verifier
Security checks for vulnerabilities and agentic risk
Overview
The skill artifacts are mostly coherent for ClawHub and Convex maintainer work, but they include high-impact automation that deserves human review before installation.
Install only if you are comfortable with maintainer-grade ClawHub/Convex workflows. Prefer opting out of the full-access review mode, review commands before running moderation or publishing actions, and avoid sending confidential diffs to fallback external reviewer tools unless that disclosure is acceptable.
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.