ClawHub
Back to skill

Security audit

飞书语音

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Feishu voice integration that openly uses Feishu and ElevenLabs APIs, with privacy considerations around voice and text handling.

Before installing, confirm that your organization permits Feishu voice content and generated reply text to be processed by ElevenLabs, review ElevenLabs logging/retention settings, and add an operational cleanup process for temporary audio files.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (6)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly sends user voice content to ElevenLabs for speech-to-text and text-to-speech processing, but the overview does not warn users that their audio and derived text leave the primary platform and are processed by a third party. This creates a privacy and consent risk, especially because voice data may contain sensitive personal or corporate information.

External Transmission

Medium
Category
Data Exfiltration
Content
用户发送语音时，收到的是 `file_key`，需要通过以下步骤下载：

```bash
TOKEN=$(curl -s -X POST "https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal" \
  -H "Content-Type: application/json; charset=utf-8" \
  -d '{"app_id":"你的app_id","app_secret":"你的app_secret"}' | grep -o '"tenant_access_token":"[^"]*"' | cut -d'"' -f4)
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
-d '{"app_id":"你的app_id","app_secret":"你的app_secret"}' | grep -o '"tenant_access_token":"[^"]*"' | cut -d'"' -f4)

# 下载语音文件
curl -s "https://open.feishu.cn/open-apis/im/v1/messages/{message_id}/resources/{file_key}?type=file" \
  -H "Authorization: Bearer $TOKEN" -o /path/to/voice.ogg
```
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
### 2.2 ElevenLabs 语音转文字

```bash
curl -s -X POST "https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true" \
  -H "xi-api-key: ${ELEVENLABS_API_KEY}" \
  -F model_id="scribe_v1" \
  -F file=@/path/to/voice.ogg
Confidence
98% confidence
Finding
This call uploads a local voice recording to ElevenLabs for speech-to-text, which is a third-party external service outside Feishu. The skill context makes this more sensitive because user voice may contain personal, biometric, or confidential business information, and the example explicitly enables provider logging via enable_logging=true, increasing data exposure risk.

External Transmission

Medium
Category
Data Exfiltration
Content
### 3.1 ElevenLabs TTS 生成

```bash
curl -s -X POST "https://api.elevenlabs.io/v1/text-to-speech/pNInz6obpgDQGcFmaJgB" \
  -H "Content-Type: application/json" \
  -H "xi-api-key: ${ELEVENLABS_API_KEY}" \
  -d '{
Confidence
95% confidence
Finding
This call sends generated text to ElevenLabs for text-to-speech. While TTS is expected functionality, the text may include sensitive user or enterprise content, so transmitting it to an external provider without an explicit warning or data-handling controls creates a real confidentiality risk.

Missing User Warnings

Low
Confidence
94% confidence
Finding
The documentation notes that temporary voice files are stored under /root/.openclaw/workspace/ but does not warn about local disk persistence, access control, or cleanup. Temporary storage of voice recordings can expose sensitive audio if the workspace is shared, backed up, or left uncleared.

Static analysis

No suspicious patterns detected.