ClawHub
Back to skill

Security audit

CommerceAI Shopping

Security checks for vulnerabilities and agentic risk

Overview

This skill provides scoped product searches through CommerceAI, with external query sharing and usage charges described in its instructions.

Shopping requests and follow-ups are sent to CommerceAI and consume credits. Omit sensitive or unrelated personal details, configure the API key outside chat, and verify prices on merchant pages. Server-side data retention is not described in the supplied artifact.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

The workflow sends the user's full request to CommerceAI without a user-facing privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The instructions require transmitting the user's full request and subsequent queries to the external CommerceAI service. Although the service and endpoint are identified, the skill does not tell the user that their request content will be shared with that third party.

Content

No source excerpt is available for this finding.