Back to skill

Security audit

Facebook Management Skills by MCBAI

Security checks for vulnerabilities and agentic risk

Overview

The skill performs the advertised Facebook Page posting tasks, but it handles powerful Page tokens and destructive public-content actions with weak safeguards.

Review before installing. Use a limited-scope Page token, prefer environment variables or a secure credential store over plaintext fb_config.json, rotate/revoke tokens regularly, avoid putting secrets in URLs, and manually confirm post IDs before any delete or reschedule action. Do not rely on the advertised comment-management commands unless the implementation is updated.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/fb_post.py:34
Finding

Facebook Access Token Exposed Through URL Query Parameters

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
README.md:25
Finding

Mutable Unpinned Package Is Downloaded and Executed During Installation

Content
View full analysis
Remediation
View remediation
install facebook-management-skills-by-mcbai ``` 2. Publish and verify the expected package integrity digest where the package manager supports it. 3. Document the expected package registry and advise users not to accept packages resolved from untrusted or overridden registries. 4. Maintain a lockfile or equivalent dependency manifest for installation tooling where feasible. 5. Provide a verified manual installation option from a fixed release archive or immutable commit, including a checksum and signature-verification instructions. 6. Review package ownership controls and enable strong multi-factor authentication for publisher accounts. 7. Advise users to perform installation as an unprivileged account and in a sandboxed or disposable environment when possible. The installer should not require administrator or root privileges. ]]>
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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (29)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Phần lớn mô tả khớp với hành vi thực tế: mã thực hiện đăng text/ảnh/carousel/video/Reels/story, hỗ trợ scheduled_publish_time, xem danh sách scheduled posts, xóa bài và reschedule. Tuy nhiên mô tả tuyên bố thêm các khả năng quản lý comment (comment vào bài, reply comment, xóa comment), nhưng trong mã không có endpoint, hàm, hay lệnh CLI nào liên quan đến comments. Đây là khác biệt chức năng đáng kể giữa mô tả và mã. Không thấy mã có năng lực ngoài phạm vi Facebook Page posting/management đã khai báo.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/get-token.md (reported line 1)May include surrounding context.

md
# Cách lấy Facebook Page Access Token

## Tổng quan

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/get-token.md (reported line 5)May include surrounding context.

md
# Cách lấy Facebook Page Access Token

## Tổng quan

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/get-token.md (reported line 22)May include surrounding context.

md
# Cách lấy Facebook Page Access Token

## Tổng quan

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/get-token.md (reported line 34)May include surrounding context.

md
# Cách lấy Facebook Page Access Token

## Tổng quan

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/get-token.md (reported line 61)May include surrounding context.

md
# Cách lấy Facebook Page Access Token

## Tổng quan

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/get-token.md (reported line 63)May include surrounding context.

md
# Cách lấy Facebook Page Access Token

## Tổng quan

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/get-token.md (reported line 87)May include surrounding context.

md
# Cách lấy Facebook Page Access Token

## Tổng quan

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · README.md (reported line 44)May include surrounding context.

md
---

## Bước 2: Lấy User Access Token tạm thời (để test)

1. Vào **[Graph API Explorer](https://developers.facebook.com/tools/explorer/)**
2. Chọn app của bạn ở dropdown

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · README.md (reported line 47)May include surrounding context.

md
---

## Bước 2: Lấy User Access Token tạm thời (để test)

1. Vào **[Graph API Explorer](https://developers.facebook.com/tools/explorer/)**
2. Chọn app của bạn ở dropdown

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

md
---

## Bước 2: Lấy User Access Token tạm thời (để test)

1. Vào **[Graph API Explorer](https://developers.facebook.com/tools/explorer/)**
2. Chọn app của bạn ở dropdown

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

md
---

## Bước 2: Lấy User Access Token tạm thời (để test)

1. Vào **[Graph API Explorer](https://developers.facebook.com/tools/explorer/)**
2. Chọn app của bạn ở dropdown

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 146)May include surrounding context.

md
---

## Bước 2: Lấy User Access Token tạm thời (để test)

1. Vào **[Graph API Explorer](https://developers.facebook.com/tools/explorer/)**
2. Chọn app của bạn ở dropdown

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/get-token.md (reported line 18)May include surrounding context.

md
---

## Bước 2: Lấy User Access Token tạm thời (để test)

1. Vào **[Graph API Explorer](https://developers.facebook.com/tools/explorer/)**
2. Chọn app của bạn ở dropdown

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/fb_post.py (reported line 256)May include surrounding context.

python
---

## Bước 2: Lấy User Access Token tạm thời (để test)

1. Vào **[Graph API Explorer](https://developers.facebook.com/tools/explorer/)**
2. Chọn app của bạn ở dropdown

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The markdown advertises deleting scheduled posts and deleting comments as supported actions, but it does not warn that these actions can remove live content or engagement and may be irreversible. For markdown files, operations affecting user data or system integrity should include explicit warnings when such behaviors are described.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The README instructs users to run npx clawhub@latest install ..., which fetches and executes the latest package version without pinning. If the upstream package is compromised or a breaking/malicious release is published, users could unknowingly execute untrusted code during installation.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill documents clear network access and likely use of local configuration/secrets, but it does not declare an explicit tool scope such as allowed tools or permissions. This increases the risk of overbroad execution in an agent environment, where a loosely scoped skill could access network or environment resources beyond what users expect.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation text is overly broad, especially the phrase covering 'any' Facebook Page content management action. In an agent setting, broad triggers can cause the skill to activate for ambiguous requests and perform sensitive posting or management actions without sufficiently precise user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation includes destructive actions such as deleting posts and comments without emphasizing irreversibility or requiring confirmation. In an automated agent workflow, lack of warning around destructive operations increases the chance of accidental or unauthorized content deletion.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The documentation exposes destructive and publicly visible actions such as immediate posting, deleting posts, and deleting comments without any warning, confirmation requirement, or operator-safety guidance. In a skill that automates Facebook Page management, this increases the chance that an agent or user triggers irreversible or reputation-impacting actions without understanding they are live or destructive.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The documentation asserts that a Page Access Token is effectively 'never expires', which overstates credential permanence and can lead operators to skip rotation, expiry monitoring, and revocation planning. If the token is later invalidated due to app, user, page, or platform changes, automation may fail unexpectedly or teams may keep a powerful token indefinitely without proper lifecycle controls.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The guide tells users to store a high-privilege Page access token in a local JSON file in plaintext, with only a warning not to commit it to Git. Plaintext local secret storage increases the chance of theft through malware, backups, shared machines, accidental uploads, logs, or misconfigured file permissions, especially because this token can post and manage page content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The script's docstrings, CLI help text, examples, status messages, and error messages are predominantly written in Vietnamese with no option to select another language. This creates a language policy issue because the skill imposes a locale on users rather than offering a choice or documenting a justified regional restriction.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The delete command performs a destructive Graph API delete immediately once a post ID is provided, with no confirmation prompt, dry-run mode, or explicit warning. In an agent/automation context, this increases the risk of accidental or prompt-induced deletion of scheduled or published content, causing integrity loss and operational disruption.

Content

No source excerpt is available for this finding.