ClawHub

Facebook Page Manager

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Facebook Page automation skill whose main risks are credential handling and public page actions, not hidden or malicious behavior.

Install only if you intend to let an agent manage a Facebook Page. Use the least permissions needed, prefer environment variables or a secret manager over fb_config.json, keep tokens out of version control, rotate or revoke tokens if exposed, and manually confirm post IDs, media, schedules, delete actions, and reschedules before running commands.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill documents network access to Facebook Graph API and use of access tokens/config files, but the metadata shown does not declare any permissions. Undeclared network/env capabilities reduce transparency and can bypass platform safety controls or user expectations about what the skill can access.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger scope includes broad phrases like 'bất kỳ thao tác post/manage nội dung trên Facebook Page,' which can cause the skill to activate for loosely related requests. Over-broad invocation increases the chance of unintended posting, editing, or deletion actions against a live Facebook Page.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill exposes deletion of scheduled posts without any explicit warning or confirmation requirement. Destructive operations against social media content can cause business impact, reputational damage, and loss of planned campaigns if invoked accidentally or via ambiguous user instructions.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
Deleting comments is a destructive moderation action that can affect user interactions, audits, and community trust, yet the description lacks an explicit warning or confirmation step. In a page-management context, accidental comment deletion can create reputational and operational issues.

Credential Access

High
Category
Privilege Escalation
Content
---

## Bước 4: Tạo Long-Lived Page Access Token (không hết hạn)

Page Access Token từ bước 3 thường **không hết hạn** nếu page đã publish và app đã qua review cơ bản.
Confidence
75% confidence
Finding
Access Token

Credential Access

High
Category
Privilege Escalation
Content
## Bước 4: Tạo Long-Lived Page Access Token (không hết hạn)

Page Access Token từ bước 3 thường **không hết hạn** nếu page đã publish và app đã qua review cơ bản.

Để chắc chắn, đổi sang long-lived token:
Confidence
80% confidence
Finding
Access Token

Credential Access

High
Category
Privilege Escalation
Content
## Bước 5: Kiểm tra token

Dán token vào [Access Token Debugger](https://developers.facebook.com/tools/debug/accesstoken/) để kiểm tra:
- Type: `PAGE`
- Expires: `Never` ✅
- Scopes có đủ permissions không
Confidence
72% confidence
Finding
Access Token

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal