Back to skill

Security audit

Groupon Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Groupon deal-finding guide that uses ordinary web search and browsing, with only a minor risk of being invoked too broadly for generic discount or activity requests.

Install this if you want the agent to search Groupon for local deals. Be aware it may bias broad discount or activity-planning requests toward Groupon results, so ask explicitly when you want non-Groupon options or broader recommendations.

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
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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README states that the agent will automatically use this skill whenever users ask about deals or discounts, which is a broad activation condition for a skill with web-browsing behavior. Overly broad triggering can cause the agent to invoke the skill in unrelated contexts, increasing the chance of unnecessary browsing, poor routing, or exposure to untrusted web content when a narrower skill would be more appropriate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The example trigger "Find something fun to do this weekend in Chicago" is broad, natural language that closely matches common everyday speech. If this skill is auto-invoked from user phrasing, it could activate unintentionally for many generic leisure-planning requests, causing scope overreach and routing users into Groupon-specific behavior when they did not explicitly ask for it.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.