Meta Ads Guide

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 6:24 AM UTC
• Version: 1.2.0

Overview

This is a plain Meta Ads workflow guide with no executable code, but users should handle any Meta access token through a secure secret flow.

Install only if you want a Meta Ads workflow router. Do not paste long-lived Meta access tokens directly into chat; use a protected secret store or OAuth-style connection when available, and grant only the minimum scopes needed for the downstream publishing or reporting task.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Credential Access

High

• Category: Privilege Escalation
• Confidence: 95% confidence

Finding

The skill explicitly instructs users to provide an Ad Account ID and an Access Token, which are sensitive credentials enabling API access to Meta Ads resources. In a skill context, asking for tokens without clear secure-handling boundaries can lead to credential exposure in prompts, logs, session memory, or downstream skills, enabling unauthorized campaign access or account modification.

Content

Scanner excerpt · SKILL.md (reported line 132)May include surrounding context.

md

## Getting Started -- First Time Setup
Before running your first campaign:

1. **Connect your Meta Ads account** -- Ad Account ID (act_XXXXXXXXX) from Ads Manager + Access Token from Meta Developer Console.
2. **Install Pixel + CAPI** -- Without these, Meta can't optimize. See meta-ads-capi-setup.
3. **Define your first campaign goal** -- Lead gen / Conversions / Link Clicks / Awareness.
4. **Set a realistic budget** -- Minimum $10-15/day per adset. See meta-ads-budget-planning.

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 85% confidence

Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 137)May include surrounding context.

md

3. **Define your first campaign goal** -- Lead gen / Conversions / Link Clicks / Awareness.
4. **Set a realistic budget** -- Minimum $10-15/day per adset. See meta-ads-budget-planning.
5. **Launch** -- meta-ads-strategy -> meta-ads-builder -> meta-ads-publisher (always launch PAUSED, review, then activate).
6. **Wait 5-7 days** -- Don't judge during Learning Phase. Changing things during Learning resets the clock.

---

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill description includes broad trigger phrases such as 'how do I use Didoo AI', 'which skill', and 'not sure where to start', which are common in normal conversation and can cause unintended invocation. In an agent ecosystem, overbroad routing increases the chance this skill activates in irrelevant contexts, potentially steering workflows, collecting context unnecessarily, or preempting more appropriate skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.