ClawHub
Back to skill

Security audit

glr-cli

Security checks for vulnerabilities and agentic risk

Overview

This skill is a GLR command-line helper with disclosed project-scoped operations, and I found no hidden or harmful behavior in the artifacts.

Install this only if you intend to let an agent operate GLR projects and run their configured project roles. Review the project manifest and role commands before use, and set GLR_NO_UPDATE_CHECK=1 if you do not want routine commands to make background release-check requests.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Ae1

High
Category
analysis-evasion
Content
`SKILL.md`; do not assume a repository checkout or a user-profile install
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Missing User Warnings

Low
Confidence
85% confidence
Finding
This markdown file documents that normal subcommands perform a background HTTP release check and cache the result, which is a network operation. Although opt-out behavior is described, the section does not clearly frame this as a privacy/network disclosure warning to users before routine command use.

Static analysis

No suspicious patterns detected.