ClawHub
Back to skill

Security audit

Meta Ads Healthcheck

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only Meta Ads health check that uses disclosed credentials to summarize campaign performance, with some consent and trigger wording that users should review.

Install only if you are comfortable giving the agent read-only access to the specified Meta Ads account's campaign and ad set performance data. Use a token limited to ads_read where possible, and invoke the skill explicitly when you want an ads health check.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

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 113)May include surrounding context.

md
When you have 10+ active campaigns:
1. Red campaigns with spend > $50/day → Check today
2. Yellow campaigns where CPL is 20%+ above target → Check today
3. New campaigns (< 7 days, still in Learning) → Flag as "Learning Phase — Do Not Judge Yet"
4. Green campaigns → Review weekly

---

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill requires a Meta access token and ad account ID to pull campaign and adset data, but it does not clearly warn that it will access potentially sensitive advertising account performance data. Users may not realize the scope of data exposure, creating a consent and transparency problem even though the OAuth scope is read-only.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill’s usage trigger includes broad, everyday language like 'any time something feels off,' which can cause over-broad activation and unintended access to Meta Ads account data in contexts where the user did not clearly request an account health check. Because this skill uses live advertising credentials, vague invocation criteria increase the chance of unnecessary or surprising data access.

Content

No source excerpt is available for this finding.