Feishu Voice Loop

• Outcome: Review
• Latest audit: May 29, 2026 at 9:24 PM UTC
• Version:
  1.0.0

Overview

The skill appears to do its advertised audio and Feishu workflow, but it needs Review because it can run a locally configured command and send user text or audio-derived content to third-party services without clear consent boundaries.

Install only if you are comfortable with the configured transcription command running locally and with your text or voice-derived content being processed by OpenAI and Feishu. Review ~/.openclaw/openclaw.json before use, keep that config protected, and avoid using regulated, secret, or highly sensitive content unless the data-flow policy is acceptable.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• 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)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

for token in model.get('args', []):
            rendered.append(token.replace('{{OutputDir}}', outdir).replace('{{MediaPath}}', str(media_path)))
        cmd.extend(rendered)
        subprocess.run(cmd, check=True)
        txt_path = Path(outdir) / f'{media_path.stem}.txt'
        if not txt_path.exists():
            candidates = list(Path(outdir).glob('*.txt'))

• Confidence: 91% confidence
• Finding: subprocess.run(cmd, check=True)

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: This skill routes user-provided text and possibly transcribed voice content to external services including OpenAI for TTS and Feishu for message delivery, but the user-facing description does not clearly disclose that data leaves the local environment. That creates a privacy and consent risk because users may provide sensitive audio or text without understanding that it will be transmitted to third parties and stored or processed under those platforms' policies.

Missing User Warnings

Medium

• Confidence: 83% confidence
• Finding: The script sends user-supplied text to OpenAI for synthesis and uploads the resulting audio to Feishu, but it provides no explicit disclosure, consent checkpoint, or content-sensitivity warning. In environments where users may pass secrets, personal data, or regulated content, this can cause unintended third-party data exposure.

VirusTotal

65/65 vendors flagged this skill as clean.