Back to skill

Security audit

Facebook Reels 搜索【Gecho 官方】

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Facebook Reels research workflow that uses Gecho's MCP and Chrome extension, with ordinary caution needed around logged-in browser access and optional saved results.

Install this only if you are comfortable using Gecho's Chrome extension and MCP bridge with a logged-in Facebook browser session. Treat saved result files as retained social-media data: choose any save directory deliberately, avoid storing data you do not need, and remove files when finished.

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
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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill supports writing collected results to a local absolute directory but does not prominently foreground that it may create persistent local files containing scraped social-media data. This creates a real privacy and user-consent risk because users may not realize data will be stored on disk, retained after the session, or written to an unexpected location.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The activation rule is broad enough to trigger on general 'research', 'structured collection', or 'platform investigation' requests, which can cause the agent to invoke this skill in contexts the user did not specifically intend. In this skill, that over-broad routing is somewhat constrained by the single-tool workflow and explicit Facebook Reels scope, so the main risk is misrouting and unnecessary data collection rather than arbitrary code execution or privilege escalation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.