Security audit
Policy Reader
Security checks across malware telemetry and agentic risk
Overview
The artifacts describe disclosed ClawHub and Convex workflow skills whose file, command, auth, and moderation capabilities are purpose-aligned and user-directed.
Install only if you want these ClawHub/Convex maintainer workflows. Review the autoreview helper before using it because it can run nested review tooling with full-access mode by default and may send diffs to configured fallback reviewer CLIs; use moderation commands only with the intended account and explicit targets.
SkillSpector
By NVIDIA
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
VirusTotal
61/61 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.