ClawHub
Back to skill

Security audit

vasp-skills

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent VASP workflow helper with disclosed templates and safety-oriented guidance, and I found no hidden or disproportionate behavior.

Before using it on a real cluster, review any generated or copied VASP inputs, confirm POTCAR/species order, module or executable names, Slurm resource requests, and which restart files are intentionally carried forward. Job submission and overwrite decisions should remain user-directed.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
- direct/fractional coordinates
- Cartesian coordinates

Do not edit coordinates without checking the active mode first.

## Cell and relaxation implications

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/poscar-species-and-structure.md (reported line 39)May include surrounding context.

md
- direct/fractional coordinates
- Cartesian coordinates

Do not edit coordinates without checking the active mode first.

## Cell and relaxation implications