ClawHub
Back to skill

Security audit

Arabic Family App RTL Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a focused Arabic/RTL app review checklist with safety guardrails and no executable code or hidden system access.

Install this when you specifically want Arabic-first or RTL app review help. As with any localization/privacy checklist, avoid sharing real family data, secrets, production credentials, or live backend access unless you have a clear reason and explicit controls in place.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 138)May include surrounding context.

md
- Do not expose private family information in examples.
- Do not print `.env` files or secrets.
- Do not run production migrations, publish app builds, or upload data without approval.
- Do not activate kids/chat/payment features unless the user explicitly approved them.
- Prefer small, reviewable changes with a real verification command.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The metadata names and categorizes the skill as specifically Arabic-focused ("Arabic Family App RTL Skill", "Arabic Apps & Localization") and reinforces that constraint through tags like "arabic" and "rtl". Because this file does not indicate any user language choice, opt-in, or region-specific justification, it presents a natural-language locale restriction that may violate the policy against forcing a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.