ClawHub
Back to skill

Security audit

tone-rewriter

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed paid tone-rewriting helper that sends user-provided text to a stated external endpoint, with no artifact evidence of hidden collection, destructive behavior, or deception.

Install only if you trust the `awal` CLI and are comfortable authenticating a payment flow. Avoid sending confidential, regulated, proprietary, or credential-like text unless you trust the external service and its data handling, and monitor usage because requests can spend USDC.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The manifest description contains broad trigger phrases such as 'tone adjustment,' 'rewrite text,' and 'formalize text,' which are common in everyday user requests and may cause the skill to be invoked too broadly. In an agent ecosystem, this increases the chance of unintended routing, unnecessary paid calls to the external x402 endpoint, and exposure of arbitrary user text to a third-party service.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.