ClawHub
Back to skill

Security audit

TencentCloud VITA

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Tencent Cloud media-analysis skill, with expected privacy and saved-prompt considerations but no artifact-backed hidden or malicious behavior.

Install this only if you intend to use TencentCloud VITA for image or video analysis. Use a dedicated API key, avoid sending private or sensitive media unless Tencent Cloud processing is acceptable, and check the saved VITA prompt if future analyses behave unexpectedly.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to write user-supplied content directly to a persistent file and overwrite any existing prompt without requiring a confirmation step or warning the user about the side effect. This creates a persistent state change that can be abused for prompt poisoning, unintended configuration changes, or silent replacement of prior settings, especially because future invocations may consume the stored prompt automatically.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script transmits user-supplied media URLs, local image contents (after base64 encoding), and prompts to Tencent Cloud, but it does not present an explicit user-facing notice or consent step at the point of transmission. In a skill that can process local files and potentially sensitive images or videos, this creates a meaningful privacy and data-handling risk because users may not realize their content is leaving the local environment.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.