Back to skill

Security audit

Hk School Selection

Security checks for vulnerabilities and agentic risk

Overview

The skill is a static Hong Kong school-selection guide with no dangerous code, but its school data is incomplete and explicitly partly unverified despite making broad recommendation claims.

Review this skill carefully before relying on it for applications. It appears safe from an agent-security perspective, but users should verify every school status, deadline, fee, language-support claim, and Banding assessment with official Education Bureau or school sources before making decisions.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (12)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The report identifies stale data and a concrete example of a closed or merged school still being presented as active with a banding classification. Because this skill provides actionable school-selection guidance for families, outdated status information can directly mislead application decisions, causing users to waste preferences or pursue nonexistent options.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This README presents all usage instructions, warnings, and examples solely in Chinese, which effectively forces a specific language for users. The policy allows locale constraints only when they are explicitly optional or clearly justified as region-specific; here the topic is Hong Kong schools, but the file does not state that Chinese is required or offer an alternative language option.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest description is entirely in Chinese and presents the skill as a general school-selection assistant, but it does not state that the skill is limited to Chinese-speaking users or offer an alternative language option. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The dataset repeatedly marks schools as "待核实" (pending verification), which conflicts with the skill's description of providing comprehensive school-selection guidance. In an education advisory context, unverified school attributes can mislead parents or students into making poor enrollment decisions, especially if the agent presents this data as authoritative.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file contains user-facing natural language content solely in Chinese, and there is no indication that the skill is region-specific by policy or that users can opt into another language. Under the language/locale policy rule, forcing a specific language without user choice can be a policy violation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The report explicitly states that the claimed '512-school database' is not actually implemented and that the underlying schools.json is missing or empty. In a school-selection skill, this creates a material integrity gap because users may rely on represented structured data and programmatic query capability that do not exist, increasing the chance of inaccurate or unverifiable guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file explicitly states a narrow target profile — '不會粵語、英語較弱、數學較強的女生(初三畢業)' — without explaining why the guidance is limited to that demographic or offering alternatives for other students. In an agent skill, this can cause inappropriate recommendations, exclusionary behavior, and biased outputs if the agent applies this profile as a default rather than asking the user for their actual circumstances.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown guide forces a specific language/locale for all users through the entire document. The file does not indicate that Chinese is optional, provide an alternative language, or explain a justified region-specific constraint, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The template hard-codes a specific target audience profile ('不會粵語、英語較弱、數學較強的女生') rather than letting the user specify or confirm these attributes. This can bias recommendations, cause inappropriate school matching, and lead to unfair or inaccurate guidance based on language ability and gender assumptions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This JSON dataset stores user-facing school metadata entirely in Chinese, including field values such as names, types, and status, with no indication that language choice is configurable or that the dataset is intentionally region-specific. Under the stated policy, a fixed language/locale can be a natural-language policy issue when there is no explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This JSON file presents the title and description only in Chinese, which can impose a language/locale choice on users without offering an alternative or documenting that the skill is intended solely for a Chinese-speaking or Hong Kong-specific audience. The policy allows locale constraints when they are clearly documented and justified, but this file does not state such a constraint explicitly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This markdown file uses a single fixed language throughout and does not indicate any alternative language option or user opt-in. Under the policy rule for language or locale constraints, forcing one language without choice can be a natural-language policy concern.

Content

No source excerpt is available for this finding.