ClawHub
Back to skill

Security audit

Tạo ảnh Infographic

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it generates infographic images through a disclosed 9Router image API script, with credentials and network use expected for that purpose.

Install only if you are comfortable letting the skill use your 9Router/OpenClaw API credentials to send image prompts to the configured 9Router endpoint. Keep prompts free of sensitive private data, verify the configured base URL, and choose a normal image output path so it does not overwrite another file.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs the agent to run a local Node.js script that calls an external API and therefore uses code execution plus network access, but it declares no permissions. This creates a least-privilege and transparency problem: an orchestrator or reviewer cannot accurately assess or constrain what the skill is allowed to do, increasing the risk of unintended outbound requests or misuse of environment-backed credentials.

Context-Inappropriate Capability

Medium
Confidence
84% confidence
Finding
The skill says it may use web-search to gather or elaborate content, which expands behavior beyond narrowly generating an image from user-provided text. That broadening increases attack surface by enabling retrieval of untrusted external content, which can introduce prompt injection, misinformation, or privacy issues if user context is sent to search tools unnecessarily.

VirusTotal

63/63 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
image-generator.js:32