Back to skill

Security audit

高考志愿填报

Security checks for vulnerabilities and agentic risk

Overview

This is a China gaokao admissions-planning skill that uses public admissions data and user-provided student preferences, with no code execution, persistence, or credential access found.

Install this only if you want help with Chinese gaokao admissions planning. Expect to provide sensitive educational details such as score, rank, subject track, preferences, tuition limits, and possibly an application table; verify final recommendations against official provincial and university admissions sources before acting.

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 (8)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 204)May include surrounding context.

md
## Line-margin methodology

Do not judge by absolute score alone.

Calculate:

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description is broad enough to trigger on many ordinary college-choice requests without tight scoping or eligibility checks. Overbroad activation can cause the agent to invoke this skill in the wrong context, leading to irrelevant data retrieval, mistaken province-specific advice, or unwarranted collection of sensitive student preference data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill is explicitly China-specific and Chinese-language-oriented, but it does not describe any user-consent or locale-selection behavior before applying those assumptions. If invoked for users in other education systems or languages, it may provide inapplicable guidance, mishandle expectations, or steer the conversation into a jurisdiction-specific workflow without confirmation.

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 presents key operational terms and guidance using Chinese-language labels and mixed Chinese text, but it does not state that the skill is intended only for Chinese-speaking users or provide any user opt-in for language/locale. This can violate language/locale policy expectations because the skill effectively assumes a specific language context without explicit choice or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The natural-language comments and title hard-code a Chinese gaokao context using Chinese-only terms such as "志愿", "物理类/历史类", and "本科批". This constrains language and locale behavior without offering a user choice or documenting that the skill is explicitly limited to a China-specific admissions workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire report template is written in Chinese and provides no indication that language choice is optional or user-selected. Under the natural-language policy rule, this can constitute a locale/language policy violation because it implicitly fixes the skill output language without opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The checklist includes the Chinese item "志愿数量" while surrounding content is in English, which imposes a specific language in the skill text without any stated user opt-in or locale justification. This can violate language/locale policy because users expecting an English-only workflow may not understand required verification steps.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction "Unverified data marked as需复核" embeds a Chinese-only label in an otherwise English checklist, with no language choice or explanation. This creates a locale-specific requirement that may be unclear to users outside that language context.

Content

No source excerpt is available for this finding.