ClawHub
Back to skill

Security audit

feishu-minimax-t2a-voice

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it turns Feishu reply text into voice audio using disclosed TTS services, with some privacy and file-location caveats.

Install only if you are comfortable sending voice-reply text to MiniMax or Edge TTS. Avoid using it for secrets or highly sensitive content, use a dedicated MiniMax API key if configured, and be aware generated audio may remain in the configured media output directory until overwritten or cleaned up.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
75% confidence
Finding
The script writes synthesized output into a hard-coded local media directory outside the temporary workspace, which is broader filesystem side-effect than required for core TTS generation. In an agent skill context, unexpected writes to a user-specific path can violate least privilege, create privacy concerns, and overwrite or expose data in another workflow.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The function transmits user-provided text to an external TTS service along with an API credential, but the code provides no user-facing consent, warning, or data classification controls. In an agent setting, users may supply sensitive content assuming local processing, making undisclosed network transmission a meaningful privacy risk.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The Edge TTS fallback sends input text to an external service without clear notice or consent controls. Because it is an automatic fallback path, users may not realize their content is being transmitted off-host after the primary provider fails.

Static analysis

No suspicious patterns detected.