Back to skill

Security audit

Nearby Bars

Security checks for vulnerabilities and agentic risk

Overview

This is a simple nearby-bar lookup skill with disclosed location use and no executable code or hidden behavior.

Before installing, note that the skill uses precise location to find nearby bars and may cache a coarse location briefly. It should only be used after location permission, and ambiguous "nightlife" requests should be clarified if the user may mean something other than bars.

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
93% confidence
Finding

The trigger term "nightlife" is broader than the stated skill scope of finding nearby bars, so the agent may invoke this skill for requests about clubs, events, adult entertainment, or general evening activities that it is not designed to handle. This can cause incorrect routing, over-collection of location context for unrelated intents, and unintended responses in sensitive contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The document presents most operational content in Chinese while also embedding English trigger phrases and labels, but it does not state that the skill is region-specific or that users can choose their preferred language. This can amount to an implicit language policy that is not justified or opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.