ClawHub
Back to skill

Security audit

Audio Content Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill’s audio-generation purpose is coherent, but its documented shell command can turn user-influenced script or topic text into executable shell syntax.

Review this before installing. It appears intended to create audio through ElevenLabs, but the documented command pattern is unsafe for adversarial or untrusted prompts because generated text and topic names may be placed into a shell command. Use only with trusted inputs or after changing the implementation to pass arguments without a shell, sanitize filenames, and store outputs in a private temporary directory.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:143
Finding

Shell Command Injection Through Untrusted Script and Filename Interpolation

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill sends generated or user-influenced script content to the external ElevenLabs service, but the description does not prominently disclose that third-party transmission occurs. Users may provide sensitive or proprietary material expecting local processing, leading to unintended data exposure to an external provider.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
61% confidence
Finding

The skill is designed to generate and return MP3 files via MEDIA tokens and save them under /tmp, but the documentation does not describe access controls, retention guarantees, or isolation for generated artifacts. If MEDIA references or temporary files are accessible beyond the intended recipient or persist longer than expected, user content could be exposed across sessions or to other local actors.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: audio-gen
description: Generate audiobooks, podcasts, or educational audio content on demand. User provides an idea or topic, Claude AI writes a script, and ElevenLabs converts it to high-quality audio. Supports multiple formats (audiobook, podcast, educational), custom lengths, and voice effects. Use when asked to create audio content, make a podcast, generate an audiobook, or produce educational audio. Returns MP3 audio file via MEDIA token.
homepage: https://github.com/clawdbot/clawdbot
metadata: {"clawdbot":{"emoji":"🎙️","requires":{"skills":["sag"],"env":["ANTHROPIC_API_KEY","ELEVENLABS_API_KEY"]},"primaryEnv":"ANTHROPIC_API_KEY"}}
---

Static analysis

No suspicious patterns detected.