Security audit

Facebook Management Skills by MCBAI

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims, but it gives an agent powerful Facebook Page posting and deletion authority with weak safeguards around tokens and irreversible actions.

Install only if you intend to let an agent manage a real Facebook Page. Use the minimum Meta permissions needed, prefer environment variables or a secret manager over `fb_config.json`, restrict file permissions, and rotate/revoke the token if exposed. Before publishing, rescheduling, or deleting, manually verify the Page ID, post/comment ID, content, media, and schedule time.

SkillSpector

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 clearly relies on network access to Facebook Graph API and handles credentials via a local config, but it does not declare permissions or capabilities explicitly. This weakens transparency and reviewability, making it easier for a powerful skill to be invoked without adequate user or platform understanding of its access needs.

Missing User Warnings

Medium

Confidence: 82% confidence
Finding: The README instructs users to store a Facebook Page Access Token in a local JSON file and includes only a narrow warning not to commit one config file to GitHub. Because these tokens grant powerful posting and engagement permissions, insufficient guidance on secret handling can lead to credential leakage through source control, logs, backups, screenshots, or permissive filesystem access.

Vague Triggers

Medium

Confidence: 80% confidence
Finding: The trigger language is very broad, including 'bất kỳ thao tác post/manage nội dung trên Facebook Page,' which can cause the skill to activate for a wide range of sensitive social-media actions. In a skill that can publish, edit schedules, and delete content, overbroad triggering increases the chance of unintended or insufficiently verified destructive actions.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The documentation includes deletion of scheduled posts without any warning, preview, or confirmation guidance. Because deleting scheduled content is irreversible from the user workflow perspective and can materially affect business communications, omission of safeguards makes accidental loss more likely.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill documents comment deletion with no caution about irreversible removal or moderation consequences. Since comment deletion affects public-facing engagement and can remove user content permanently, missing confirmation and audit guidance creates avoidable operational and trust risks.

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: 76% confidence
Finding: This section explicitly encourages creation and use of a long-lived or effectively non-expiring Page Access Token. Persistent high-privilege tokens materially increase the blast radius of accidental leakage or compromise, enabling long-term unauthorized posting, deletion, and page management if the token is exposed.

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: 84% confidence
Finding: The statement that the Page Token 'không hết hạn'/'never expires' normalizes use of non-expiring credentials for a powerful content-management integration. In the context of a skill that can post, schedule, comment, and delete content, a stolen token could provide durable unauthorized control over a Facebook Page.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: references/get-token.md:78