ClawHub
Back to skill

Security audit

Lazyads

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent LazyAds integration, but it gives agents live ad campaign and budget-changing authority without strong confirmation or safety boundaries.

Install only if you want an agent to manage connected advertising accounts. Before using mutating tools, require explicit confirmation for campaign creation, launch, pause/resume, budget, bid, targeting, automation, and creative spend actions, and keep the LazyAds API key scoped, private, and revocable.

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 (2)

Credential Access

High
Category
Privilege Escalation
Content
2. Connect your ad platform accounts in the Lazy Ads dashboard (ChatGPT Ads can also be connected with `connect_chatgpt_ads` using an Ads Manager API key; every other platform uses dashboard OAuth or BYO-key cards)
3. Generate an API key at Settings → API (https://lazyads.ai/dashboard/settings?tab=api) and store it:
   ```
   # ~/.hermes/.env
   LAZY_ADS_API_KEY=la_your_api_key
   ```
4. Add the server to `~/.hermes/config.yaml` (see https://lazyads.ai/hermes):
Confidence
60% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill advertises create, update, pause, budget, bidding, and launch capabilities across connected ad platforms, but the referenced usage section does not prominently warn that these actions can immediately affect live campaigns and incur real spend. In an agent context, missing an explicit spend/modification warning increases the risk of unsafe automation, unintended launches, or budget changes being executed without clear user confirmation.

Static analysis

No suspicious patterns detected.