ClawHub
Back to skill

Security audit

Read Github Tool Free

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed repository-reading helper, but users should be careful with its outbound URL and callback options.

Install only if you are comfortable with the agent contacting gitmcp.io and any external URLs you ask it to fetch. Avoid using callback_url unless you trust the destination and understand what data will be sent there.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill advertises fetching external URLs referenced by repository documentation without clearly warning that this causes outbound requests to arbitrary third-party domains. In an agent context, this can leak user IP/environment metadata, trigger access to attacker-controlled infrastructure, or be abused for SSRF-like network reachability if internal URLs or sensitive endpoints are ever permitted.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
Documenting a callback_url parameter without any warning or constraints creates a meaningful exfiltration risk because processed results or status data may be sent to an arbitrary destination. In an agent workflow, an attacker could supply a callback endpoint they control and cause sensitive repository contents, prompts, or execution metadata to be transmitted off-platform.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.