Bot Voice Config Clean

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:19 PM UTC
• Version:
  1.1.0

Overview

This skill is a coherent voice-configuration helper that uses disclosed Volcengine TTS and Feishu integrations, but users should handle the required API credentials carefully.

Install only if you intend to connect this skill to Volcengine and Feishu. Use least-privileged Feishu app permissions, avoid putting real secrets in shared dotfiles or committed config files, restrict config file permissions, and test with non-sensitive text because generated audio is sent to third-party services.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The README explicitly describes generating audio and sending it to Feishu while also requiring users to provide and store sensitive API credentials, but it does not clearly warn that user-provided text or generated content will be transmitted to third-party services. In an agent-skill context, this can lead to unintentional disclosure of sensitive prompts, conversation data, or secrets to external platforms, especially if users assume the skill operates locally.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The README explicitly instructs users to export long-lived secrets such as VOLC_API_KEY, FEISHU_APP_ID, and FEISHU_APP_SECRET in shell startup files like ~/.bashrc or ~/.zshrc. Persisting credentials in broadly reused startup files increases the chance of accidental disclosure through shared dotfiles, backups, screen sharing, shell debugging, or inheritance by unrelated processes, and the documentation provides no warning or safer alternative.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill documentation instructs users to place Feishu and Volcengine credentials directly into environment variables and a JSON config file under the workspace, including app secrets and API keys. Storing secrets in plaintext configuration files without explicit secret-handling guidance increases the risk of credential leakage through filesystem exposure, backups, logs, screenshots, or accidental commits.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill advertises generating test audio and sending it to Feishu, but provides no privacy or consent warning about transmitting potentially sensitive text/audio content to a third-party messaging platform. If users test with real customer, employee, or confidential content, this can create unnecessary data exposure and retention risks outside the primary system boundary.

VirusTotal

66/66 vendors flagged this skill as clean.