ClawHub
Back to skill

Security audit

code-to-images

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local code-to-image/PDF converter, with no evidence of hidden execution, exfiltration, persistence, or destructive behavior.

Install only if you are comfortable running a local Python script and the listed npm/pip dependencies. Before running, review and edit the `FILES` list so it processes only intended files, and avoid manually running the `_fix_*` maintenance scripts unless you specifically want them to edit markdown documentation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
96% confidence
Finding
The skill invokes local file reads/writes and shell-based tooling (`npm install`, `pip install`, and running a Python script) but does not declare any permissions. That is dangerous because users and enforcement layers cannot accurately assess or constrain the skill’s real capabilities, increasing the chance of unexpected file modification or command execution in the host environment.

Tp4

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding
The documented behavior does not fully match the skill’s actual functionality: static analysis indicates it also rewrites documentation files and relies on a hardcoded file list rather than acting as a general-purpose converter. Hidden or undocumented write behavior is risky because a user invoking a file conversion skill would not reasonably expect README.md/SKILL.md edits, which can lead to integrity issues or accidental tampering with repository contents.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.