ClawHub
Back to skill

Security audit

Questions Form

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Telegram form pattern that collects user-provided answers and does not install code, persist data, or access local secrets.

Before installing, understand that free-text answers typed into Telegram may include sensitive details if users provide them. Use enumerated options where possible and avoid asking for passwords, payment data, government IDs, or confidential business secrets through this form pattern.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs the agent to collect arbitrary free-text responses over Telegram via the 'Other' path, but it provides no warning to users not to include sensitive data and no guardrails to restrict collection to non-sensitive information. Because this skill is generic and intended for onboarding, requirements gathering, and preference collection, users may reasonably disclose personal, financial, or confidential business details through a third-party messaging channel, increasing privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.