Feishu Voice Sender (ZheYanyan)

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:39 PM UTC
• Version:
  1.0.0

Overview

This skill does what it says: it uses Feishu credentials to upload a chosen audio file and send it as a Feishu voice message.

Install only if you intend to let this skill use your local OpenClaw Feishu app credentials to upload selected audio files and send Feishu messages. Keep the Feishu app permissions narrow, protect ~/.openclaw/openclaw.json, and verify the file path and recipient ID before running it.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Context-Inappropriate Capability

Medium

• Confidence: 92% confidence
• Finding: The script reads Feishu app credentials from ~/.openclaw/openclaw.json even though the visible interface only advertises sending an audio file. This creates implicit access to locally stored secrets without explicit user disclosure or consent, which expands the trust boundary and could enable unintended credential use if the skill is invoked in a broader agent context.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The documentation instructs users to send audio to Feishu and the code later reads Feishu credentials from local config, but the skill does not clearly warn that audio content, recipient identifiers, and authentication-derived requests will be transmitted to a third-party service. In a messaging skill, this omission increases the risk of accidental sensitive-data disclosure because users may treat it as a local formatting/conversion tool rather than an uploader/sender.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The code silently consumes credentials from a local OpenClaw configuration file without warning the user at runtime. In an agent or automation setting, undisclosed secret access is dangerous because users may not realize the skill can authenticate as their Feishu application and perform API actions on their behalf.

VirusTotal

67/67 vendors flagged this skill as clean.