ClawHub
Back to skill

Security audit

FAQ Schema Content Builder

Security checks for vulnerabilities and agentic risk

Overview

The bundled script reports duplicate FAQ questions locally, with no evidence of hidden access, automatic downloads, or harmful behavior.

Use a dedicated output directory because duplicates.md is overwritten. Expect separate work to produce and validate the FAQ page and JSON-LD. The optional unsigned Windows executable is outside this review; assess it independently before running it, including checking the [publisher's release page](https://github.com/rapidworker1/Multiple-AI-models-Toolkit/releases/tag/Main).

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 (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Question deduplication is relevant to the declared workflow, but the supplied executable only produces duplicates.md. It never renders FAQ content, processes answers for publication, or creates structured data. Its actual output therefore materially falls short of the declared primary purpose. No unrelated resource access or malicious behavior is evident.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

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.