ClawHub
Back to skill

Security audit

Jimeng Image Skill Openclaw

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it sends an image prompt to the Jimeng/Volcengine API using user-provided credentials and saves the returned PNG locally.

Install only if you are comfortable providing Jimeng/Volcengine API credentials and sending image prompts to that provider. Use a dedicated API key where possible, avoid confidential prompt content, and manage or delete generated files in the output directory if they are sensitive.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
78% confidence
Finding
The trigger conditions are vague and overly broad, which can cause an agent to invoke the skill in situations the user did not clearly intend. That increases the chance of unnecessary API usage, unintended credential use, and unexpected generation or file creation side effects.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill instructs the agent to use stored API credentials and save generated files locally without warning about privacy, billing, persistence, or disclosure risks. In an agent environment, silent use of secrets and automatic filesystem writes can expose sensitive prompts or create unexpected costs and retained artifacts.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal