ClawHub
Back to skill

Security audit

github-initiative-pulse

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only GitHub reporting helper with broad triggers, but no hidden execution, persistence, credential handling, or destructive behavior in the artifact.

Installers should understand this skill may trigger on general GitHub, reporting, dashboard, project, or status requests. Review any generated GitHub comments, labels, issue follow-ups, or CSV/report content before posting or applying it, especially because the skill assumes external tracker.py and GitHub workflows that are not included in this package.

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 (2)

Vague Triggers

Medium
Confidence
97% confidence
Finding
The manifest trigger list contains generic words like "github," "projects," "reporting," "status," and "dashboards" without constraints or negative examples. These terms overlap with common everyday work requests and make it unclear when this specific skill should activate versus other GitHub or reporting-related skills.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
70% confidence
Finding
Shadow Command Trigger: 'status' conflicts with built-in command 'status'

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.