ClawHub
Back to skill

Security audit

infinimo-ai-design-product-image-create

Security checks across malware telemetry and agentic risk

Overview

This is a transparent Infinimo image-generation API helper, with expected network upload and token use for that purpose.

Install only if you are comfortable sending prompts, product images, reference URLs, and an Infinimo API token to the clawec.com/Infinimo service. Do not use confidential, regulated, or customer-identifying assets unless your organization permits it, and treat the documented delete endpoint as a manual destructive action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill documents shell-based scripts and executable workflow steps but does not declare corresponding permissions or clearly scope what execution capabilities are required. This can mislead users and hosting systems about the skill's operational surface, reducing review visibility and increasing the chance of unsafe command execution or unvetted network actions through helper scripts.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The workflow instructs users to upload reference images and submit prompts to a third-party API but does not warn that potentially sensitive product assets, branding materials, or embedded metadata will leave the local environment. This creates a privacy and data-governance risk because users may unknowingly transmit confidential or regulated content to an external service.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill documents a delete endpoint for image logs without any warning, confirmation, or explanation of permanence. This is dangerous because an agent or user could remove generation history or result references unintentionally, causing loss of artifacts, auditability, or recoverability.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The script silently transmits user-supplied prompts, image references, and an authentication token to a third-party endpoint without any explicit user-facing disclosure or confirmation. In a skill context, users may reasonably assume local processing unless told otherwise, so this creates a privacy and data-handling risk, especially if prompts or image URLs contain sensitive commercial or personal information.

External Transmission

Medium
Category
Data Exfiltration
Content
print(json.dumps(body, ensure_ascii=False))
' "$PROMPT" "$MODEL" "$RATIO" "$SIZE" "$IMAGES" "$TARGET_PLATFORM" "$REGION" "$SCENE")

curl -s -X POST "https://www.clawec.com/api/aigc/ec_media/image/create" \
  -H "Token: $TOKEN" \
  -H "Content-Type: application/json" \
  -d "$PAYLOAD"
Confidence
93% confidence
Finding
curl -s -X POST "https://www.clawec.com/api/aigc/ec_media/image/create" \ -H "Token: $TOKEN" \ -H "Content-Type: application/json" \ -d

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.