ClawHub
Back to skill

Security audit

Redline Contract

Security checks across malware telemetry and agentic risk

Overview

This is a local contract-redlining helper that reads user-selected DOCX files and writes review outputs, with no evidence of hidden network access or malicious behavior.

Install this only if you are comfortable processing confidential contracts locally and generating sidecar files that include contract text, comments, and proposed legal language. Keep originals, avoid overwriting important files, review all tracked changes and risk reports before sharing, and install Python dependencies only from trusted sources.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.