ClawHub
Back to skill

Security audit

Outlit SDK

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Outlit analytics integration guide, with privacy-sensitive tracking behavior that users should configure deliberately.

Before installing, make sure you want Outlit tracking added to the target app and decide whether tracking should be consent-gated. Review which events, identifiers, form-derived identity fields, and properties will be sent to Outlit, and avoid sending secrets or unnecessary personal data.

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 (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly promotes browser tracking behaviors including visitor storage and auto-identification from form fields, but does not present a prominent upfront privacy warning before encouraging implementation. In a code-assistant skill, this omission can cause developers to enable collection of personal data without fully understanding consent, disclosure, and regulatory implications.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs users to verify outbound event delivery to Outlit endpoints and frames this as normal setup, but it does not clearly warn that application and user data will be transmitted to a third-party service. This can lead to unreviewed exfiltration of behavioral, identity, or account data to an external vendor during integration.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
|-----------|----------------|
| Existing CMP/cookie banner | Initialize with `autoTrack: false`; call `enableTracking()` from the CMP accept callback and `disableTracking()` on revoke/decline |
| EU/privacy signals but no CMP | Use `autoTrack: false` and tell the user they need a consent decision; do not build a CMP unless asked |
| No consent requirement found | Use default `autoTrack: true` |

Explain the tradeoff: `autoTrack: true` creates browser visitor storage immediately. `autoTrack: false` waits until `enableTracking()` is called.
Confidence
83% confidence
Finding
The skill makes an autonomous policy decision that if no consent requirement is found, tracking should default to auto-enabled, despite incomplete visibility into legal, jurisdictional, and product-specific privacy obligations. In this context, that is dangerous because the agent may activate storage and telemetry collection without explicit user confirmation or a validated compliance review.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.