ClawHub
Back to skill

Security audit

Privacy Scan

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently sends a user-provided public URL to a remote privacy-scanning service and does not install code, persist locally, or request unrelated access.

Install this only if you are comfortable sending the URLs you scan to privacy-scan.foomworks.workers.dev. Avoid scanning private, sensitive, or unpublished pages unless you trust that external service.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

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 8)May include surrounding context.

md
openclaw:
    requires:
      bins:
        - curl
homepage: https://privacy-scan.foomworks.workers.dev
license: MIT
---

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

md
- "Audit this page's privacy posture — trackers, consent tooling, cookie attributes, HTTPS"

## What it checks (static-HTML signals)
Third-party trackers present with no consent tooling (GDPR/ePrivacy), missing privacy-policy link
(GDPR/CCPA), missing CCPA "Do Not Sell or Share" link when trackers are present, insecure cookie
attributes (Set-Cookie without Secure/SameSite), not-HTTPS / mixed content. It recognises common
trackers (Google Analytics/Tag Manager, Meta Pixel, TikTok, Hotjar, Clarity, LinkedIn, …) and

Static analysis

No suspicious patterns detected.