ClawHub
Back to skill

Security audit

Social Proof Collector

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it helps collect and reuse public customer reviews, but users should confirm they are allowed to scrape and republish that content.

Before installing, use this only with review sources you are authorized to access and republish. Prefer official APIs or user-owned exports, avoid storing unnecessary reviewer personal data, keep attribution intact, and review each platform's terms before placing review text or reviewer names in widgets, email, or social posts.

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
Confidence
90% confidence
Finding
The skill explicitly instructs scraping and extracting reviewer names, review text, dates, and platform sources from multiple third-party review platforms, then republishing that content in widgets, social posts, and alerts. This creates privacy, copyright/licensing, and platform-terms risks because it encourages collection and reuse of third-party content without any safeguards, consent checks, retention limits, or compliance guidance.

Static analysis

No suspicious patterns detected.