ClawHub
Back to skill

Security audit

Audiobook

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims: it helps generate audiobooks by sending text to SenseAudio's TTS API and saving audio files locally.

Install only if you are comfortable sending the text you convert to SenseAudio's external API. Avoid confidential, regulated, private, or rights-restricted manuscripts unless you have approval, and remember that generated MP3 and metadata files remain on disk until you remove them.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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 (3)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill sends user-provided text to a third-party TTS service and writes generated audio to local files, but the user-facing guidance in this section does not clearly warn about either behavior. This creates a privacy and data-handling risk because users may provide copyrighted, sensitive, or confidential text without informed consent, and local file writes can persist that data-derived output on disk unexpectedly.

External Transmission

Medium
Category
Data Exfiltration
Content
import binascii

def generate_audio_segment(text, voice_id, output_file, speed=1.0):
    url = "https://api.senseaudio.cn/v1/t2a_v2"
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
Confidence
92% confidence
Finding
The hardcoded third-party API endpoint indicates the skill is designed to send content to an external service outside the user's environment. While expected for cloud TTS, this becomes dangerous when users assume processing is local or do not realize their long-form text is being shared with an external provider.

External Transmission

Medium
Category
Data Exfiltration
Content
}
    }

    response = requests.post(url, headers=headers, json=payload)
    data = response.json()

    # Decode hex audio
Confidence
95% confidence
Finding
This code performs an outbound HTTP request to SenseAudio with the full text payload, which means any supplied content leaves the local environment and is exposed to third-party processing. In an audiobook skill, that behavior is functionally necessary, but it is still security-relevant because books, manuscripts, internal training material, or personal documents may be sensitive or copyrighted.

Static analysis

No suspicious patterns detected.