ClawHub
Back to skill

Security audit

记忆秘书

Security checks across malware telemetry and agentic risk

Overview

The scanned artifacts look like disclosed ClawHub CLI/operator documentation, and the flagged force-update examples are not presented as a malware-warning bypass.

Reasonable to install if you trust ClawHub registry tooling. Review any use of --force before running it because it can overwrite local skill files, and protect CLI auth tokens because they may authorize publishing or moderation actions.

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
Findings (1)

Ssd 3

Medium
Confidence
98% confidence
Finding
The README explicitly tells users to bypass malware reputation warnings using a force-install flag and frames VirusTotal detections as mere false positives. Even without code execution in the README itself, this guidance undermines a key safety control and can socially engineer users into installing a potentially malicious package without verification.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.