Back to skill

Security audit

Facebook Scraper

Security checks for vulnerabilities and agentic risk

Overview

This skill is openly a Facebook scraper, but it includes guidance for bypassing platform limits and collecting/storing contact data at scale.

Review this skill carefully before installing. Use it only for data you are authorized to collect, avoid attempts to bypass Facebook rate limits or account/IP blocks, protect proxy and API credentials as secrets, and define clear limits for what contact data and images are stored, who can access them, and when they are deleted.

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
Findings (1)

other

Warning
Location
SKILL.md:200
Finding

Guidance for Anti-Detection and Facebook Rate-Limit Evasion

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly documents exporting scraped Facebook page/group data to JSON/CSV and downloading thumbnails locally, including fields such as phone, email, address, website, and images, but does not clearly warn operators that this may constitute collection and local storage of potentially sensitive personal or business contact data. In an agentic scraping context, this omission increases the risk of unintentional overcollection, insecure retention, or mishandling of scraped data by users who may not realize what is being stored on disk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to place proxy usernames and passwords in environment variables and shows example values, but provides no warning that these are sensitive secrets that can leak through shell history, logs, process listings, CI output, or misconfigured environments. Because the same section encourages long-running automated scraping with third-party proxy services, exposed credentials could be abused to consume paid proxy bandwidth, impersonate the operator's scraping activity, or expose operational infrastructure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.