ClawHub
Back to skill

Security audit

Piper TTS

Security checks for vulnerabilities and agentic risk

Overview

This local Piper text-to-speech skill has a coherent purpose, but its vague trigger rules and missing referenced shell scripts create a real risk of unintended or uninspectable command execution.

Review this skill before installing. Only use it for explicit local TTS or voice-message requests, and do not allow an agent to run scripts/setup-piper.sh or scripts/piper-speak.sh unless you have verified the exact script files being executed. Expect local package installation, voice-model downloads, and MP3 files if the setup is completed.

SkillSpector

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 (3)

Vague Triggers

High
Confidence
92% confidence
Finding
The activation condition is incomplete and ambiguous: 'Use when。触发关键词...' does not clearly define the boundaries for when the skill should or should not run. Ambiguity in invocation logic makes accidental routing more likely, especially because the skill later references executable scripts, so unrelated requests could trigger shell-based actions under an overly permissive interpretation.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation condition is incomplete and ambiguous: 'Use when。触发关键词...' does not clearly define the boundaries for when the skill should or should not run. Ambiguity in invocation logic makes accidental routing more likely, especially because the skill later references executable scripts, so unrelated requests could trigger shell-based actions under an overly permissive interpretation.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The core capability section repeats vague trigger language and an incomplete phrase ('the user asks for voice res'), reinforcing unclear selection behavior rather than constraining it. Repetition of broad, underspecified triggers increases the chance that the agent will prioritize this skill for unrelated requests, which is risky because the skill includes operational instructions to run local scripts.

Static analysis

No suspicious patterns detected.