ClawHub
Back to skill

Security audit

MolQL

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent MolQL translation skill; the included publishing helper is disclosed and does not run automatically.

Install this if you want an agent-side reference for translating molecular structure selections into MolQL. Only run the bundled publishing script if you intentionally want to publish the skill and understand which ClawHub account or token it will use.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

There is a clear mismatch between the declared purpose and the actual code chunk. The description describes runtime functionality for translating natural language molecular structure requests into MolQL expressions. The code provided does not implement any translation, parsing, molecular selection logic, or ambiguity handling. Instead, it is an operational shell script for publishing the skill to a registry/platform. That is a materially different primary purpose and an undeclared capability relative to the description.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.