ClawHub
Back to skill

Security audit

Deals ToMe

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only deal-curation helper with disclosed public sources and no evidence of code execution, credential use, persistence, or destructive behavior.

Before installing, consider whether you want generic shopping and deal requests to trigger this skill, and treat the personalized result as a recommendation whose data basis is not specified in the 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Natural-Language Policy Violations

Medium
Confidence
81% confidence
Finding
The skill promises a 'personalized' result category but provides no indication of user opt-in, data sources, or whether personalization can be declined. Even without obvious sensitive data handling in this file, this creates a privacy and transparency risk because users may receive behaviorally tailored recommendations without informed consent or clear control.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The intent list is broad enough to match generic shopping or deal-seeking requests without clear geographic, source, or task boundaries. That can cause over-triggering of the skill, leading users to receive marketplace-driven outputs when they did not explicitly request this skill, which is a scope and consent problem even if the skill is read-only.

Static analysis

No suspicious patterns detected.