ClawHub
Back to skill

Security audit

Hebrew Nikud

Security checks for vulnerabilities and agentic risk

Overview

This is a static Hebrew pronunciation reference with no tool access, code execution, network behavior, persistence, or data access.

Install this only if you want the agent to consult a Hebrew nikud reference for pronunciation-sensitive Hebrew text. It does not request tools or system access, but users should still verify linguistic output because incorrect nikud can change pronunciation or meaning.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The description states this skill should be used for adding Hebrew nikud to text, especially for TTS, which effectively constrains language behavior to Hebrew. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy violation unless the region/language constraint is explicitly justified as opt-in or scoped.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.