ClawHub
Back to skill

Security audit

Volcengine Ata Subtitle

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Volcengine subtitle-alignment CLI, with expected privacy and credential-handling cautions.

Install only if you are comfortable sending the chosen audio and transcript text to Volcengine or another explicitly configured ATA endpoint. Use a protected token, prefer secure environment/secret handling or a config file with restrictive permissions, and avoid processing confidential or regulated recordings without authorization.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill documentation describes capabilities that read environment variables and local files, write output files, and make outbound network requests, but it does not declare permissions for those actions. That creates a transparency and consent problem: users and hosting platforms cannot accurately evaluate what the skill will access before execution, especially since it handles credentials and uploads user-provided audio/text to an external service.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The README describes uploading audio and accompanying text to Volcengine's external ATA service, but it does not clearly warn users that their media and transcript content leave the local device and are processed by a third party. This can lead to unintended disclosure of sensitive audio, personal data, or confidential text, especially in an automation context where users may assume processing is local.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill markets subtitle generation but does not clearly disclose that user audio, subtitle text, and authentication material are sent to Volcengine's third-party API. In this context, that omission is security-relevant because users may provide sensitive recordings or transcripts without informed consent about external transmission and processing.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The tool uploads full audio and subtitle text to a third-party API, which can expose sensitive speech content, transcripts, or proprietary media if users are unaware of the transfer. In a subtitle-generation skill this behavior is expected, but the lack of an explicit disclosure/consent step increases privacy risk, especially when inputs may contain confidential material.

Session Persistence

Medium
Category
Rogue Agent
Content
## Prerequisites

Set the following environment variables or create a config file:

### Option A: Environment Variables
Confidence
88% confidence
Finding
create a config file: ### Option A: Environment Variables ```bash export VOLC_ATA_APP_ID="your-app-id" export VOLC_ATA_TOKEN="your-access-token" export VOLC_ATA_API_BASE="https://openspeech.bytedanc

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.