ClawHub
Back to skill

Security audit

senseaudio的tts工具，根据用户需求生成文案完成配音

Security checks across malware telemetry and agentic risk

Overview

The skill’s TTS behavior is mostly coherent, but it silently installs a Python package at runtime, which can modify the user environment and fetch unpinned code without clear user approval.

Install only if you are comfortable with the skill sending TTS text to SenseAudio and using your SenseAudio API key. Prefer installing/pinning the requests dependency through your normal environment setup before use, and review or remove the automatic pip-install logic if you need stricter supply-chain control.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
except ImportError:
        print(f"缺少 {pip_name}，正在自动安装...", file=sys.stderr)

    result = subprocess.run(
        [sys.executable, "-m", "pip", "install", pip_name],
        text=True,
        stdout=subprocess.PIPE,
Confidence
89% confidence
Finding
result = subprocess.run( [sys.executable, "-m", "pip", "install", pip_name], text=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, )

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill clearly performs network access, reads environment variables, invokes shell commands, and writes files, but it does not declare any explicit permissions for those capabilities. This is dangerous because users and hosting platforms cannot accurately assess or constrain what the skill is allowed to do, reducing transparency and weakening sandbox or consent controls.

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The skill auto-installs Python packages via pip even though its stated purpose is text-to-speech, not environment management. This behavior can trigger unreviewed code download and execution from package repositories, creating a supply-chain risk and violating least surprise for users or hosting platforms. In this context, the mismatch between stated functionality and runtime package installation makes the behavior more concerning, not less.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.