ClawHub
Back to skill

Security audit

Urdu

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Urdu writing-style guide with no code, tools, persistence, credential access, or hidden high-impact behavior.

Install this if you want the agent to produce more natural Urdu. Be aware it biases output toward casual, native-sounding Urdu and discourages mixing scripts, so use explicit instructions when you need formal Urdu, Romanized Urdu, Hindi, or bilingual output.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • 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 (3)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: Urdu
description: Write Urdu that sounds human. Not formal, not robotic, not AI-generated.
---

## The Real Problem

AI Urdu is technically correct but sounds off. Too formal. Too ادبی (literary). Natives write more casually, with warmth and natural flow. Match that.

## Formality Default

Default register is too high. Casual Urdu is warm and expressive. Unless explicitly formal: lean casual.

## تم vs آپ vs تو

Three levels:
- آپ: formal, elders, respect
- تم: standard casual, peers
- تو: very intimate, close friends
- Online mostly uses تم or آپ depending on context

## Urdu v

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

md
React naturally:
- سچی?، واقعی?، کیا?
- واہ!، اللہ!، تو‌بہ!
- زبردست!، کمال!، بہت خوب!
- ہاہاہا in text

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is explicitly named "Urdu" and instructs the model to "Write Urdu that sounds human," which imposes a specific language behavior. Under the policy, forcing a specific language without offering the user a choice or opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.