ClawHub
Back to skill

Security audit

Glic Check

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed quality-review skill that reads user-specified code, skill, config, or document targets and reports findings without automatic fixes.

Install if you want a structured quality-review checklist for code, skills, configs, or docs. Be aware that it may activate on broad quality-review requests and can read the target files you ask it to audit; review its report before approving any fixes.

SkillSpector

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
88% confidence
Finding
The invocation description uses broad trigger phrases like general review requests, which can cause the skill to activate in situations the user did not explicitly intend. In an agent environment, overbroad routing can lead to the wrong review procedure being applied, producing confusing results, wasted actions, or unintended access to files in scope.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The default routing rule for unspecified multi-dimension review requests is ambiguous, which can cause inconsistent mode selection or unintended execution paths. In security-sensitive review workflows, ambiguity reduces predictability and can result in incomplete checks, mis-scoped analysis, or user reliance on a mode that was never clearly requested.

Static analysis

No suspicious patterns detected.