ClawHub
Back to skill

Security audit

article-tts

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed OCR-to-speech helper, with the main caution being that users can opt to skip review before sending generated audio.

Keep confirmation enabled for private, financial, medical, or confidential images. Before sending, verify the active chat channel and recipient, and remember that generated text/audio may be saved locally and TTS content may be processed by the Edge TTS service.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
94% confidence
Finding
The documented skip-confirmation flow explicitly allows OCR-extracted text to be converted to audio and sent over the active messaging channel without a human review step. Because OCR input can contain sensitive or misrecognized content, this increases the risk of unintended disclosure to third-party chat platforms or the wrong recipient.

Static analysis

No suspicious patterns detected.