ClawHub
Back to skill

Security audit

Huo15 Xhs Pgy Test

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent PGY blogger-research purpose, but it asks an agent to handle a PGY password and scrape logged-in page text without enough safeguards.

Review before installing. Use this only for a PGY account you are authorized to access, avoid sharing passwords in chat if a browser-only login is possible, and check generated reports for sensitive or unnecessary account-gated data before saving or sharing them.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill explicitly requires the user to provide a PGY account and password, but it includes no warning, safer authentication alternative, or guidance on minimizing exposure of credentials. This is especially risky because the skill automates login to a third-party platform and then extracts account-gated profile, demographic, and pricing data, so credential mishandling could expose both the user's account and sensitive commercial information.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The alias "pgy" is extremely broad and can match many unrelated user utterances, increasing the chance this skill is invoked outside its intended Xiaohongshu PGY context. Because the skill performs browser automation and credentialed login flows, accidental activation could cause inappropriate credential prompts, unintended browsing actions, or data collection against the wrong task.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The guide explicitly instructs an automated agent to enter account credentials and later extract large portions of page text from a logged-in platform. In this context, broad innerText scraping can capture sensitive business, account, or demographic data beyond the minimum needed, and there are no guardrails about consent, least-privilege access, redaction, or secure credential handling.

Content

No source excerpt is available for this finding.