Security audit
JD Shopping
Security checks across malware telemetry and agentic risk
Overview
The skill set contains disclosed ClawHub and Convex workflow helpers, including admin actions, with clear user-confirmation guardrails and no evidence of hidden exfiltration or persistence.
Install only if you expect ClawHub/Convex staff and repository-maintenance workflows. Reviewers should pay particular attention before using the moderation, email, production migration, or autoreview model-invocation helpers, because they can affect accounts, public content, production data, or send code diffs to configured AI providers when explicitly invoked.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.