ClawHub
Back to skill

Security audit

xiaomi-mimo-v2-tts

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward text-to-speech helper that sends provided text to Xiaomi MiMo's API and writes the returned WAV file locally.

Install only if you are comfortable sending the text you synthesize, any optional context, and your MiMo API key to Xiaomi MiMo's API. Avoid using it for secrets, private records, or sensitive personal content unless that matches your data-sharing expectations.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description says to use the skill when the user asks to "convert text to speech, generate audio, read text aloud ... or create voice files." Phrases like "generate audio" and "create voice files" are broad and can overlap with many unrelated user requests, making activation scope insufficiently specific for a manifest/markdown file.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/tts.py (reported line 12)May include surrounding context.

python
import urllib.request
import urllib.error

API_BASE = "https://api.xiaomimimo.com/v1"
MODEL = "mimo-v2-tts"

VOICES = ["mimo_default", "default_zh", "default_en"]

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill sends arbitrary input text and optional user-supplied context to a third-party TTS service, but the code provides no explicit disclosure, consent flow, redaction, or warning that this content leaves the local environment. Because users may provide sensitive text for speech generation, this creates a real privacy and data-handling risk even though the external call is necessary for the skill's function.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.