ClawHub
Back to skill

Security audit

Meta Ads Report

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only Meta Ads reporting skill that clearly asks the user to supply their own Meta token and uses it for disclosed Graph API report calls.

Install only if you are comfortable giving the agent read access to your Meta Ads reporting data. Use a token with ads_read only unless you have a separate, clear reason for broader permissions, keep the token out of chat and commits, and rotate or remove it from the gateway config when no longer needed.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

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 28)May include surrounding context.

md
1. Vào `https://developers.facebook.com/tools/explorer` trên máy/trình duyệt của bạn
2. Chọn app loại **Business** (của bạn)
3. Tích quyền **`ads_read`** (thêm `ads_management` nếu cần)
4. Bấm **Generate Access Token** → đăng nhập Facebook → Cho phép
5. Copy chuỗi token nhận được — **giữ riêng, không chia sẻ**

> Token ở bước này chỉ sống **~2 giờ**. Muốn dùng lâu (~60 ngày) phải đổi sang long-lived token (xem mục cuối file).

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 29)May include surrounding context.

md
1. Vào `https://developers.facebook.com/tools/explorer` trên máy/trình duyệt của bạn
2. Chọn app loại **Business** (của bạn)
3. Tích quyền **`ads_read`** (thêm `ads_management` nếu cần)
4. Bấm **Generate Access Token** → đăng nhập Facebook → Cho phép
5. Copy chuỗi token nhận được — **giữ riêng, không chia sẻ**

> Token ở bước này chỉ sống **~2 giờ**. Muốn dùng lâu (~60 ngày) phải đổi sang long-lived token (xem mục cuối file).

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 16)May include surrounding context.

md
| Biến | Bắt buộc | Mô tả |
|------|----------|-------|
| `META_ACCESS_TOKEN` | ✅ | Meta access token (User token hoặc System User token), quyền `ads_read` |
| `META_AD_ACCOUNT_ID` | ✅ | Ad account ID dạng số (không có prefix `act_`), ví dụ `123456789` |

**Lưu ý bảo mật:**

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README's instructional content is entirely in Vietnamese, including setup and operational guidance for agents and users. This imposes a language constraint without any opt-in, alternative language, or stated region-specific justification, which matches the natural-language policy violation criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.