ClawHub
Back to skill

Security audit

Flux Image

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward FLUX image-generation helper with normal cloud-service and CLI-install risks that users should understand.

Install only if you trust inference.sh and are comfortable with its CLI installer. Prefer reviewing the installer or using the manual checksum path, and do not submit confidential prompts, private image URLs, secrets, personal data, or sensitive images unless that third-party processing is acceptable for your workflow.

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
90% confidence
Finding
The trigger list includes very broad terms such as "flux," "flux ai," and "black forest labs," which can match ordinary discussion and cause the skill to activate outside the user's intent. Over-broad activation can route unrelated prompts into this skill, increasing the chance of unnecessary remote image-generation actions or disclosure of user content to the external service.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation shows prompts and image URLs being sent to inference.sh but does not clearly warn users that their text and referenced images are transmitted to a remote third-party service. In this context, accidental activation is already made more likely by broad triggers, so the missing disclosure increases privacy risk because users may unknowingly send sensitive prompts, proprietary images, or internal URLs off-platform.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.