ClawHub
Back to skill

Security audit

Amber Mmgbsa

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Amber MM/GBSA workflow guide with local, purpose-aligned commands and no hidden persistence or data transfer behavior.

Before installing, users should be comfortable running local AmberTools commands that create project files and logs. Review ligand charge, input structures, and output interpretation carefully, but no security-sensitive behavior was identified.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding
Suspicious Unicode normalization or mixed-script content

Natural-Language Policy Violations

Low
Confidence
93% confidence
Finding
Line L103 contains the Chinese term "缓冲" embedded in English instructions. This creates an avoidable language/locale inconsistency and may confuse users who did not opt into mixed-language content.

Static analysis

No suspicious patterns detected.