Back to skill

Security audit

Gaokao Volunteer Advisor

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its stated gaokao advising purpose, but its generated HTML report can include unescaped user or web text that may execute in a browser.

Review this skill before installing if you plan to generate or share HTML reports. The publisher should require HTML escaping or safe templating for every dynamic value, and users should avoid pasting untrusted HTML-like content into report fields until that is fixed.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
templates/report-template.html:242
Finding

Unescaped Dynamic Content in Generated HTML Report

Content
View full analysis
生成日期:{{生成日期}} 省份:{{省份}} 批次:{{批次}} ``` ```html
{{一句话结论}}
``` ```html
省份 / 年份
{{省份}} / {{年份}}
科类 / 选科
{{科类}}
分数
{{分数}}
位次
{{位次}}
批次
{{批次}}
风险偏好
{{风险偏好}}
城市偏好
{{城市偏好}}
专业偏好
{{专业偏好}}
限制条件
{{限制条件}}
``` Additional affected sinks include school names, descriptions, notes, risk descriptions, action items, and uploaded filenames. ### Technical Analysis The report-generation procedure treat ...[truncated 2808 chars]
Remediation
View remediation
` as `>` - `"` as `"` - `'` as `'` 2. Replace unrestricted textual substitution with a maintained template engine that enables contextual auto-escaping by default. 3. Treat user input, uploaded-file values, and retrieved web content as untrusted data. Add an explicit instruction that such content must never be interpreted as HTML or executable instructions. 4. If limited rich formatting is required, sanitize it with a strict allowlist. Reject scripts, inline event handlers, dangerous URL schemes, forms, iframes, embedded objects, SVG content, and CSS capable of loading remote resources. 5. Add a restrictive Content Security Policy to the template, such as: ```html ``` 6. Avoid inserting dynamic values into raw HTML attributes. If this becomes necessary, apply context-specific attribute and URL encoding in addition to general HTML escaping. 7. Add regression tests that generate reports using payloads such as: ```html ``` Verify that each payload appears only as inert visible text and that no outbound requests, event handlers, or scripts execute. ]]>
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (9)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description is entirely written as a Chinese-only skill description and frames the skill for Chinese gaokao advising, but it does not explicitly state that responses will be in Chinese by default with user opt-in for other languages. Under the policy, forcing a specific language without user choice can be a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill file is written as mandatory guidance in Chinese and includes fixed reminder text to output, but it does not indicate that users may choose another language or that the Chinese-only constraint is optional. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The HTML root sets lang="zh-CN", and the entire template content is written in Chinese, which imposes a specific language/locale on users. The file does not indicate that this locale is optional, user-selected, or justified as a region-specific-only skill, so it conflicts with the policy against forcing a language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file presents all guidance in Chinese and does not indicate that the user can choose another language or that the skill is intentionally restricted to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This file presents all instructions and search templates only in Chinese, with no indication that the user can choose another language or that the restriction is intentionally limited to a Chinese-speaking audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This playbook presents all instructions and examples only in Chinese, with no note that the user can choose another language or that the skill is intended solely for a Chinese-speaking audience. Under the language/locale policy, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The entire document is written in Chinese and provides no indication that language selection is optional or that the skill is explicitly limited to Chinese-speaking users. Under the policy rule for natural-language violations, a file that forces a specific language without user opt-in can be flagged unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

This markdown file is entirely in Chinese and does not indicate that the user can choose another language or that the skill is intentionally restricted to a Chinese-speaking audience. Under the language/locale policy, forcing a single language without opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The entire skill is written in Chinese and does not indicate that users may interact in another language or choose a locale. Under the policy, a skill that implicitly enforces a specific language without opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.