ClawHub
Back to skill

Security audit

AdMakeAI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AdMakeAI API helper for creating ads, checking ad data, and optionally pushing drafts or uploads to Meta with user confirmation.

Install this only if you intend to let an agent use your AdMakeAI API key for ad workflows. Review prompts carefully before approving credit-spending generation, uploads, or Meta campaign draft pushes, and avoid using it for unrelated generic create/list/find requests.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list is excessively broad and includes common verbs like 'create', 'make', 'get', 'find', and 'list', which can cause the skill to activate for loosely related requests. In this skill, unintended invocation is more dangerous because the capability set includes networked reads, credit-spending generations, and writes to external advertising platforms, increasing the chance of accidental external actions or unnecessary API usage.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
84% confidence
Finding

The skill documentation broadly instructs that 'every tool' is callable and then enumerates a large allowlist that includes both read-only operations and externally impactful writes such as Meta uploads and campaign draft pushes. Although the text warns to confirm dangerous actions, the capability surface is still expansive and increases the risk of over-privileged or mistaken tool selection, especially when combined with broad triggers.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

md
`Authorization: Bearer <key>` also works. Never echo the key back to the user or paste it into a file.

## How to call

Every tool has one canonical tRPC dotted path — `adGeneration.create`. Two transports expose the same allowlist:

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 82)May include surrounding context.

bash
# 1. find the project (brand) to generate for
curl -H "x-api-key: $ADMAKEAI_API_KEY" \
  https://admakeai.com/api/v1/adResearch.listProjects

# 2. create an ad image