SiliconFlow TTS Gen

• Outcome: Pass
• Latest audit: May 28, 2026, 11:36 AM
• Version:
  1.0.0

Overview

This skill coherently turns text into speech through SiliconFlow and saves an audio file, with the main cautions being API-key use, external text transmission, and caller-chosen output paths.

Install only if you are comfortable sending the text you convert to SiliconFlow under your API key. Use a limited API key if possible, verify any OpenClaw config key it may auto-detect, and choose output paths carefully so generated audio does not overwrite important files.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill declares access to an environment variable and a local config file and instructs users to run a local Python script, but it does not declare explicit permissions despite capabilities equivalent to env access, file read, and shell execution. This creates a transparency and trust problem: users may supply an API key and invoke the script without clear permission boundaries, increasing the chance of unintended secret exposure or local file access if the implementation is later changed or reviewed insufficiently.

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: The skill silently reads an API key from the environment or local OpenClaw config, which means it accesses credentials without clear user-facing disclosure at the point of use. In an agent-skill context, silent credential access is sensitive because users may not realize the skill will consume locally available secrets for outbound requests.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: User-provided text is sent to a third-party API and the returned content is written to disk without any explicit warning or confirmation. In a skill environment, this is a meaningful privacy and data-handling issue because users may input sensitive text assuming local-only processing.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger pattern "tts" is very generic and likely to appear in many unrelated user requests, which can cause the skill to be invoked unexpectedly. Because this skill has access to the exec tool and requires an API key, unintended activation increases the chance of unnecessary command execution, accidental external API use, and leakage of user intent or sensitive text to the TTS provider.

VirusTotal

64/64 vendors flagged this skill as clean.