ClawHub
Back to skill

Security audit

ladybug-opencypher

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Ladybug/openCypher reference and optional local helper script package, with no hidden install, persistence, or exfiltration behavior found.

Install only if you intend to work with Ladybug/openCypher. Review Cypher before running it, especially DDL, COPY/LOAD, CALL procedures, or FTS/httpfs-related queries, because those actions may modify a local database or read files according to Ladybug behavior.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared description presents a functional Ladybug/openCypher execution skill for writing, debugging, importing, and comparing Cypher queries. In contrast, the actual code does not connect to a database, execute Cypher, manage DDL, perform imports, expose FTS features, or handle Neo4j compatibility. Its sole purpose is to validate that the real_ladybug Python bindings are installed and expose expected classes. That is a materially different primary purpose, so this is a clear mismatch.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared description presents a comprehensive Ladybug/openCypher skill with multiple specialized capabilities and guidance areas. The supplied code only provides a simple synchronous command-line executor for Cypher against a local Ladybug database file. While generic execution could incidentally run DDL, CALL statements, or FTS-related commands if the backend supports them, the script itself does not implement the specialized features, async behavior, migration notes, or workflow support claimed in the description. This is a description-to-behavior mismatch because the actual code is materially narrower than the declared purpose.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.