Social Media Metrics

• Outcome: Review
• Latest audit: May 29, 2026 · 9:24 PM UTC
• Version: 1.0.2

Overview

This skill appears intended to fetch social follower counts, but it uses anti-detection browser automation and stores reusable logged-in browser sessions, so users should review it before installing.

Install only if you are comfortable with browser scraping and possible platform anti-bot or account-risk consequences. Use a dedicated low-risk account for Xiaohongshu, keep the profile private, and delete ~/.playwright_cdp_profile when you no longer want retained cookies.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (10)

Context-Inappropriate Capability

Medium

• Confidence: 95% confidence
• Finding: The code explicitly states it is designed to bypass automation detection and then reuses a persistent browser profile so cookies survive across runs. In an agent skill context, that combination materially increases the risk of stealthy browsing, impersonation of a logged-in user session, and access to content gated by prior authentication without clear consent or disclosure.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The README explicitly instructs users to authenticate a real Chrome profile and states that cookies are persisted in a local profile directory, but it does not warn about the security implications of storing active session material on disk. Persistent browser sessions can be reused by other local users, malware, backups, or accidentally shared home directories, which increases the risk of account compromise if the profile is not protected.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill explicitly instructs users to authenticate Xiaohongshu in a persistent Chrome profile and notes that cookies will be reused on later runs, but this sensitive behavior is not surfaced as a prominent warning in the main description or prerequisites. Persisted authenticated browser state can expose session tokens and account access to later runs, other local users, or other components that can access the profile directory.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The PRD explicitly requires opening a browser to scrape platform data when no API is available, but it does not disclose external network access, scraping behavior, or possible privacy/compliance implications. In an agent skill context, this can cause unexpected outbound requests to third-party platforms and collection of profile-related data without adequate user warning or policy constraints.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: Launching Chrome with a fixed persistent user-data directory means cookies and session state are intentionally retained and reused across executions. That can expose prior authenticated sessions to later tasks, enable unintended cross-task data access, and create privacy and authorization risks if the agent visits sites on behalf of a user without strong isolation controls.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The code launches a real Chrome process specifically to avoid Playwright automation fingerprints, which is a stealth-oriented design choice rather than normal browser automation. In a skill with no clearly justified purpose for evasion, this makes abuse more plausible by helping automated actions blend in and reducing transparency to websites and users.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

requests>=2.31.0
playwright>=1.40.0
beautifulsoup4>=4.12.0

• Confidence: 95% confidence
• Finding: requests>=2.31.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

requests>=2.31.0
playwright>=1.40.0
beautifulsoup4>=4.12.0

• Confidence: 95% confidence
• Finding: playwright>=1.40.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

requests>=2.31.0
playwright>=1.40.0
beautifulsoup4>=4.12.0

• Confidence: 93% confidence
• Finding: beautifulsoup4>=4.12.0

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High

• Category: Supply Chain
• Confidence: 90% confidence
• Finding: requests

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.