ClawHub
Back to skill

Security audit

Ukrainian

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Ukrainian writing-style skill with no code, tools, network access, credentials, or persistence.

Install this if you want Ukrainian writing to sound more casual and native-like. Be aware it may push tone toward informal Ukrainian unless the user or task asks for a formal register.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
For a markdown skill file, invocation guidance should be specific enough to avoid unintended activation. This description is broad and lacks concrete trigger phrases, scope constraints, or negative examples clarifying when the skill should or should not be used.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
Natural-language policy violations include forcing a specific language without user opt-in. The file presents Ukrainian as the required output mode and repeatedly instructs the model to prefer that language/register, but does not state that the user can choose another language or explicitly opt in.

Static analysis

No suspicious patterns detected.