Back to skill

Security audit

Tencent Yuanbao Gaokao - Regional Passing Scores

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward GaoKao score-line lookup skill that runs a bundled Python script and queries a Tencent education endpoint, with no evidence of hidden access or persistence.

Install this if you want a Chinese GaoKao score-line lookup assistant and are comfortable with query details being sent to Tencent's GaoKao data endpoint. The package would benefit from clearer allowed-tool and network-disclosure metadata, but the inspected behavior is purpose-aligned.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (15)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill content, including required user-facing prompt text at L24 and all operating instructions, is written as mandatory Chinese-language behavior. There is no indication that the user can opt into another language or that the language restriction is explicitly justified as a region-specific policy requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This Python file contains natural-language documentation and CLI help text in Chinese, which effectively forces a specific language for users without any opt-in or alternative locale support. The stated policy flags language or locale constraints when the skill does not offer a user choice or explain why the restriction is required.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The argument parser descriptions, warnings, and final output strings are all presented only in Chinese. Because the file does not provide a language selection mechanism or a documented justification for a Chinese-only interface, this matches the policy's language/locale violation criterion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This JSON file contains only Chinese-language category labels and provides no indication that users can choose another language or that the locale restriction is intentional. Under the policy rule for natural-language violations, forcing a specific language without opt-in can be a locale policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

This manifest-style JSON consists entirely of Chinese category and value labels, with no indication that the skill is region-specific or that users can opt into this locale. Under the policy rule for language/locale, hard-coding a single language can be a natural-language policy concern when no choice or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The JSON file contains only Chinese-language category labels and provides no indication of language choice, fallback, or locale scoping. Under the policy, a skill artifact that effectively enforces a single language without opt-in can be considered a natural-language policy issue unless the regional constraint is documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This JSON file consists entirely of Chinese-language string values for region score-line titles, which enforces a single language/locale in the skill data. Under the policy, language constraints should offer user choice or be clearly documented as region-specific; this file provides no such opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The JSON value "含粤语" explicitly references inclusion of Cantonese as a language/locale constraint. In a generic reference list with no surrounding justification or user opt-in, this can represent a locale-specific policy choice embedded in data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The entries "藏文类" and "彝文类" define language-specific categories. Because this file is standalone reference data and does not include any explanation that these are region-specific or user-selected options, they appear as embedded locale constraints.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The values "藏文专业" and "彝文专业" are language-specific program labels. Without nearby documentation establishing regional justification or user choice, they can be interpreted as hard-coded locale/language constraints.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The entry "民族工艺美术(含藏文)" includes a specific language inclusion requirement. In isolation, this is a locale-specific constraint with no explicit justification or opt-in described in the file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The value "民族工艺美术(藏文)" is explicitly language-specific. Since the file provides no explanatory scope or opt-in mechanism, it may violate the requirement to avoid forcing locale/language constraints without justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entry "播音与主持艺术(蒙授)" indicates a Mongolian-medium instruction or language-specific variant. The file itself does not explain that this is an optional or region-specific official label, so it appears as an embedded locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The value "蒙授播音与主持艺术" explicitly denotes a Mongolian-language variant. Without context in the file explaining regional applicability or user selection, this is a locale-specific constraint that may conflict with language-choice policy.

Content

No source excerpt is available for this finding.