Back to skill

Security audit

Hong Kong Urbix Events

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public URBTIX event listings, caches them locally, and does not show hidden credential access, privilege escalation, or destructive behavior.

Before installing, expect the skill to contact the URBTIX public XML distribution endpoint and store event-feed cache files locally. Use it for public event lookups; no credentials are required.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The main query interface sets language='en' by default and documents only two supported languages, which means the skill will answer in English unless the caller explicitly specifies otherwise. This is a natural-language locale choice imposed by the skill rather than derived from user preference.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The usage text explicitly limits the language option to en|zh, which is a natural-language locale restriction. The file does not indicate that this constraint is optional, user-configurable beyond those two choices, or justified as a region-specific requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The --lang argument uses choices=["en", "zh"], which hard-codes a two-language policy in the skill behavior. Because no opt-in rationale or documented regional justification is provided in the file, this is a locale policy limitation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.