ClawHub
Back to skill

Security audit

妙达语音转文字

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward audio-to-text command reference with no bundled code, persistence, hidden installation, or unrelated authority.

Before installing, confirm you trust `miaoda-studio-cli` and understand where it sends or stores audio. Avoid using it on confidential recordings unless the CLI's data handling matches your privacy requirements.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list includes many broad, everyday phrases such as 'transcribe', 'voice to text', and common Chinese equivalents, which increases the chance the agent invokes this skill in situations the user did not specifically intend. Unintended invocation is especially relevant here because the skill handles user audio files and may cause accidental processing of sensitive recordings.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill does not warn users that audio supplied for transcription may be transmitted to an external CLI-backed service or otherwise processed outside the immediate conversation context. Because audio often contains sensitive personal, business, or regulated information, lack of transparency can lead to unintended disclosure and privacy harm.

Static analysis

No suspicious patterns detected.