Back to skill

Security audit

HongKong

Security checks for vulnerabilities and agentic risk

Overview

This is a Hong Kong travel-planning skill with local notes and no executable code, network behavior, or hidden high-impact authority.

Before installing, be aware that the skill can keep Hong Kong trip preferences locally in ~/hongkong/ and may ask whether it should proactively help whenever Hong Kong is mentioned. Decline or limit that opt-in if you only want it used for direct travel-planning requests.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (6)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · memory-template.md (reported line 14)May include surrounding context.

md
areas:

## Style
<!-- foodie, city, nightlife, family, outdoors, mix -->

## Group
<!-- solo, couple, family, friends, business -->

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The title explicitly fixes the skill to 'HongKong', which is a locale-specific constraint. The file does not offer any user choice of region or explain why the locale restriction is required, which can violate the policy against forcing a specific locale without opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instruction to read this file when ~/hongkong/ doesn't exist or is empty creates a broad, state-based activation condition that is not clearly tied to explicit user intent. This can cause the skill to activate opportunistically during normal operation, leading to unintended memory use or conversational steering even when the user did not ask for Hong Kong assistance.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The opt-in phrase "Want me to jump in whenever Hong Kong comes up?" is overly broad because 'Hong Kong' may arise in many ordinary conversations unrelated to requesting this skill. Once enabled, the skill could insert itself into future discussions unexpectedly, causing persistent unsolicited intervention and possibly unnecessary memory-triggered behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The template hard-codes a Hong Kong-specific destination and file naming in natural language, which can amount to a locale constraint without any opt-in or explanation. Under the policy, locale restrictions should either be optional for the user or clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The title explicitly scopes the skill to "HongKong," which is a locale constraint expressed in natural language. The file does not offer any user choice or opt-in for alternative locales, and no justification for the locale restriction is stated in the content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.