ClawHub
Back to skill

Security audit

glr-cli

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent guide for operating the GLR command-line runtime, with update and execution steps disclosed and scoped to GLR projects.

Install only if you intend to use GLR with an existing reviewed project. Before running commands, inspect the project manifest and role commands, and only run GLR updates when you explicitly want the GLR binaries and project-owned skills updated.

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

Natural-Language Policy Violations

Low
Confidence
79% confidence
Finding
The command example hard-codes a non-default language string (`土地庙`) as part of the documented usage. While this is only an example, it can signal a locale-specific assumption without offering language choice or explaining that multilingual input is optional, which may conflict with organizational language/locale policy guidance.

Static analysis

No suspicious patterns detected.