ClawHub
Back to skill

Security audit

Chemvision

Security checks for vulnerabilities and agentic risk

Overview

This chemistry skill is mostly purpose-aligned, but it needs review because it gives conflicting statements about whether chemistry queries stay local or may be sent to PubChem/OPSIN.

Install only if you are comfortable with chemical names, SMILES strings, and reaction queries potentially being processed through a local service that may query PubChem/OPSIN. Avoid confidential or proprietary chemistry queries unless the service implementation is audited or configured for truly local-only operation.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
---
name: chemvision
description: Use this skill when the user asks about chemistry — chemical names, molecular structures (SMILES), molecular formulas, molecular weights, safety information (GHS hazards), or chemical reaction predictions. Supports Chinese and English chemical names, IUPAC names, and common names. Calls PubChem and OPSIN real chemistry databases to reduce LLM hallucinations. Returns molecular structure images and chemical equation renderings.
metadata:

Intent-Code Divergence

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The documentation states that chemistry data 'never leaves the machine,' but the skill description explicitly says it uses PubChem and OPSIN, which are external databases. This creates a clear data-flow misrepresentation that can cause users or operators to submit sensitive queries under false privacy assumptions, resulting in unintended disclosure to third parties.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

name_to_structure

bash
curl -s -X POST http://localhost:8899/api/tools/call \
  -H "Content-Type: application/json" \
  -d '{"tool_name":"name_to_structure","arguments":{"name":"苯甲酸"}}'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The markdown instructs the agent to send files with fixed Chinese captions ("分子结构图" and "化学方程式"). This imposes a specific language on user-facing output without indicating that the user can choose their preferred language.

Content

No source excerpt is available for this finding.