ClawHub
Back to skill

Security audit

jimeng generator

Security checks across malware telemetry and agentic risk

Overview

This appears to be a normal Volcengine image-generation/editing skill, but users should treat prompts, image URLs, and cloud keys as sensitive.

Install only if you are comfortable sending prompts, referenced image URLs, and any uploaded/reference images to Volcengine for processing. Use least-privilege or short-lived keys when possible, keep .env files out of git, rotate keys if exposed, and avoid submitting confidential images, secrets, internal-only URLs, or proprietary prompts unless your policy permits it.

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
87% confidence
Finding
The README encourages use of prompt text and external image URLs for editing/compositing, but does not clearly warn that these inputs are transmitted to Volcengine's remote service. Users may unknowingly send sensitive prompts, internal URLs, or proprietary images to a third party, creating confidentiality and privacy risks.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill instructs users to place real cloud credentials in a local .env file and send prompts/images to an external Volcengine service, but it does not warn about secret handling, least-privilege credential use, or the privacy implications of uploading potentially sensitive content. This increases the risk of credential misuse, accidental exposure, and unintentional transfer of private images or prompts to a third party.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/generate.ts:31