Back to skill

Security audit

SZZG007 Facebook Engage

Security checks for vulnerabilities and agentic risk

Overview

This skill openly automates Facebook follows and comments, but it needs review because it can publicly act from the user's account without a clear final confirmation step.

Install only if you are comfortable letting the agent use your logged-in Facebook session to publicly follow pages and post comments. Before each run, confirm the exact Facebook URL and final comment text yourself; avoid using it for bulk engagement or anything that could look like spam or violate platform rules.

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

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill performs public actions on the user's behalf—following an account and posting a visible comment—without an explicit warning or consent checkpoint about account-impacting behavior. That is dangerous because it can cause reputational harm, unwanted endorsements, spam-like activity, or platform policy violations, especially since the skill also includes guidance on avoiding detection and making comments appear natural.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are broad enough to activate on generic social-media engagement requests, which increases the chance the agent will perform account-affecting actions in situations where the user did not explicitly ask for automated following and commenting. In this context, the skill is designed to impersonate normal user engagement at scale, so broad matching materially raises the risk of unintended spammy or policy-violating actions.

Content

No source excerpt is available for this finding.