ClawHub
Back to skill

Security audit

AdWhiz

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed hosted ad-management connector with powerful account-changing tools, but its access and data flows are coherent with its purpose.

Install only if you are comfortable granting AdWhiz the ability to read and change the specific Google Ads and Meta Ads accounts you connect. Review write confirmations carefully, especially for budget changes, activation/removal actions, and customer list uploads, and revoke access from AdWhiz if you stop using it.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
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 32)May include surrounding context.

md
## Security & Permissions Model

- **OAuth 2.0**: User authenticates with Google and/or Meta via AdWhiz's web
  UI. Refresh tokens (Google) and long-lived access tokens (Meta) are encrypted
  at rest (AES-256-GCM) and never exposed to the agent.
- **API key scoping**: Each `ADWHIZ_API_KEY` is bound to a single user's
  connected accounts. Cross-user access is not possible.

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 250)May include surrounding context.

bash
# Example: list campaigns via REST API
curl -X POST https://mcp.adwhiz.ai/api/v1/tools/list_campaigns \
  -H "Authorization: Bearer $ADWHIZ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"customer_id": "1234567890"}'

Static analysis

No suspicious patterns detected.