ClawHub
Back to skill

Security audit

vasp-input-generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent VASP input-file helper that writes local calculation templates and does not show hidden, network, credential, persistence, or destructive behavior.

Installers should understand that this skill can create or overwrite VASP input files in the selected output directory, so use it in a working folder or back up existing INCAR and KPOINTS files before running it.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is scoped to 'any other VASP-related tasks,' which is overly broad and can cause the agent to invoke this skill in situations beyond safe, well-defined input generation. Broad trigger language increases the chance of inappropriate activation, incorrect file generation, or misuse in contexts where more constrained validation or domain-specific review is needed.

Ae4

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

Ae4

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

Static analysis

No suspicious patterns detected.