Langgraph Code Review
Security checks across malware telemetry and agentic risk
Overview
The skills appear legitimate, but they include powerful maintainer workflows that can run nested review agents with full local access and perform admin moderation actions.
Install only if you need ClawHub maintainer or Convex operator workflows. Before using autoreview, consider disabling full-access mode with its no-yolo option unless you explicitly want a nested reviewer to run without sandbox prompts. Use the moderation skill only with the intended staff credentials, explicit targets, and a clear reason, because its commands can affect public listings and user accounts.
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
66/66 vendors flagged this skill as clean.