ClawHub
Back to skill

Security audit

Dead Link Scanner

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward dead-link checker whose local file reads and web requests match its stated purpose.

Install only if you are comfortable with the skill contacting links it finds in websites or local files. Use options like --internal-only, --max-urls, --depth, and --delay for private, large, or untrusted scans.

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
94% confidence
Finding
The skill documentation describes functionality that reads local files and performs outbound network requests, but it does not declare any permissions for those capabilities. Missing permission declarations can cause the agent platform or users to underestimate what the skill can access, reducing transparency and weakening review and consent controls. In this case the behavior is aligned with the stated purpose of scanning files and URLs, so the issue appears to be an undeclared-capability problem rather than overtly malicious behavior.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal