ClawHub
Back to skill

Security audit

super-github-s

Security checks across malware telemetry and agentic risk

Overview

This is a small GitHub CLI helper with no executable payload, but its description contains unrelated words that users should treat as sloppy scoping.

Install only if you want the agent to use your local GitHub CLI. Keep commands scoped with --repo or explicit URLs, review any write-capable gh or gh api command before it runs, and consider asking the publisher to remove the unrelated words from the description.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The manifest description includes unrelated, low-specificity text appended to an otherwise legitimate GitHub skill description. This kind of trigger stuffing can make the skill match unintended user requests, causing over-broad invocation and increasing the chance the agent selects this skill in inappropriate contexts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.