ClawHub
Back to skill

Security audit

PixelLetter

Security checks across malware telemetry and agentic risk

Overview

The submitted skill artifacts are coherent maintainer and Convex workflow helpers with disclosed command use and no evidence of hidden exfiltration, persistence, or destructive behavior.

Install only if you want agent assistance with ClawHub maintainer and Convex development workflows. Pay particular attention before running moderation commands, proof publishing, auth setup, package installs, or the autoreview helper's default full-access nested review mode; use the documented confirmation and opt-out controls when appropriate.

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.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/pixelletter.mjs:6