ClawHub
Back to skill

Security audit

Token Safety Checker

Security checks across malware telemetry and agentic risk

Overview

This skill is a local secret-audit and migration tool whose sensitive file edits are disclosed and aligned with its purpose.

Install only if you are comfortable with a local tool reading your OpenClaw config and, after confirmation, editing both openclaw.json and your shell profile. Review the dry run, confirm the profile path, protect or remove the .bak file when rollback is no longer needed, and prefer file- or exec-based SecretRef for higher-security environments.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
Findings (1)

Description-Behavior Mismatch

Medium
Confidence
98% confidence
Finding
The skill claims to migrate plaintext secrets into safer SecretRef usage, but it persists the raw secret values into the user's shell profile, which is another plaintext storage location. This can expose credentials to other local users, backups, dotfile syncing, terminal history workflows, and accidental source-control inclusion, undermining the security goal of the tool.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.