ClawHub
Back to skill

Security audit

DFT input file generator

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only CP2K input drafting skill with local structure-file use and no executable code, persistence, credential access, or hidden external behavior.

Review generated CP2K inputs before running them, especially charge, spin, periodicity, k-points, and convergence settings. Installing this skill does not appear to add code execution or external data access beyond reading local structure files you provide.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · references/cp2k-task-map.md (reported line 299)May include surrounding context.

md
## 9. Non-goals for automatic routing

These tasks should not be silently auto-generated from a vague one-line prompt without warning:
- NEB / CI-NEB / transition-state search
- excited-state workflows beyond basic documented templates
- GW / RPA / MP2 / double hybrids

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The 'When to use this skill' section says to use the skill when the user 'describes a simulation in natural language' or asks for 'a simple CP2K setup,' which are broad conditions that could overlap with many chemistry conversations. The file does not provide negative examples or tighter boundaries for when such requests should not invoke the skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown includes Chinese-only example requests and mixed English/Chinese trigger mappings as part of the skill’s ambiguity handling, but it does not state that users may interact in their preferred language or that multilingual handling is optional. Under the language/locale policy, embedding a specific language expectation without explicit opt-in can be a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file hard-codes English and Chinese phrases as the recognized user expressions for task and priority defaults. This introduces a language-specific behavior policy without stating that users may choose their preferred language or that other locales are supported.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.