Mimo Stt Publish

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This plugin appears to do the advertised speech-to-text job, but it uploads the selected local audio file and MiMo API key to an external endpoint, so users should configure it carefully.

This looks like a normal API-backed speech-to-text plugin. Before enabling it, confirm you trust the MiMo endpoint, provide a dedicated API key if possible, and only let it process audio files you intend to upload for transcription.

Static analysis

Env credential access

Critical

Finding: Environment variable access combined with network send.
Content: const apiKey = api.pluginConfig?.apiKey || process.env.MIMO_API_KEY;

Env credential access

Critical

Finding: Environment variable access combined with network send.
Content: const KEY = process.env.MIMO_API_KEY;

Exposed secret literal

Critical

Finding: File appears to expose a hardcoded API secret or token.
Content: const apiKey = [REDACTED]?.apiKey || process.env.MIMO_API_KEY;

VirusTotal

VirusTotal engine telemetry is currently stale for this artifact.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

ASI02: Tool Misuse and Exploitation

Low

What this means

If the agent or user passes the wrong path, the plugin could upload a non-audio or unintended local file to the configured STT endpoint.

Why it was flagged

The tool caller supplies a local path that the plugin reads and transcribes. This is expected for speech-to-text, but there is no artifact evidence of path, file type, or size enforcement.

Skill content

filePath: Type.String({ description: "音频文件的本地路径" }) ... readFileSync(params.filePath); ... const result = await transcribe(params.filePath);

Recommendation

Use the tool only with intended audio attachments; the publisher should restrict paths to OpenClaw-provided audio files and validate extension/MIME/size.

ASI03: Identity and Privilege Abuse

Low

What this means

Your MiMo API key is used by this plugin to make transcription requests.

Why it was flagged

The plugin uses a MiMo API credential and sends it as an API header to the configured endpoint. This is necessary for the integration and is described in the configuration section.

Skill content

const apiKey = api.pluginConfig?.apiKey || process.env.MIMO_API_KEY; ... headers: { "Content-Type": "application/json", "api-key": apiKey }

Recommendation

Use a dedicated MiMo API key if possible, keep it out of shared logs/configs, and only configure trusted endpoints.

ASI07: Insecure Inter-Agent Communication

Low

What this means

Audio contents are transmitted to the configured MiMo-compatible service for transcription.

Why it was flagged

Audio content is sent to an external provider endpoint, and the endpoint can be configured. This is purpose-aligned, but it is a sensitive data boundary users should understand.

Skill content

const apiBase = api.pluginConfig?.apiBase || process.env.MIMO_API_BASE || "https://api.xiaomimimo.com"; ... fetch(`${apiBase}/v1/chat/completions`, { ... body: JSON.stringify(body) })

Recommendation

Keep the default official endpoint unless you trust an alternate API base, and avoid sending private audio you do not want processed by that service.

ASI09: Human-Agent Trust Exploitation

Low

What this means

A user might assume the plugin can only contact the official Xiaomi endpoint, even though configuration can redirect requests.

Why it was flagged

This safety wording is mostly accurate for the default configuration, but the code and plugin schema allow a configurable apiBase, so the official endpoint is not enforced by the artifact.

Skill content

No external network calls except to Xiaomi official API

Recommendation

The publisher should clarify that the official endpoint is the default and warn users to configure only trusted apiBase values.

ASI04: Agentic Supply Chain Vulnerabilities

Info

What this means

The registry summary may understate that this skill runs plugin code and needs Node/API configuration.

Why it was flagged

The included files define executable plugin code and a package dependency, so the registry install summary appears incomplete. The artifacts do not show a remote install script or hidden helper.

Skill content

Install specifications: No install spec — this is an instruction-only skill.

Recommendation

Review the included source and configuration files before enabling; the registry metadata should be updated to match the plugin requirements.