Back to skill

Security audit

exam-mindmap-generator

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent study-plan purpose, but it under-discloses risky behavior such as remote script loading, unsafe HTML generation, authority-like instructions, and overwrite behavior.

Install only if you are comfortable with a Chinese-language skill that writes and may overwrite an HTML report, loads ECharts from bootcdn.net when the report is opened, and embeds study data into the page. Prefer a version that bundles dependencies locally, escapes all knowledge-map content, removes authority-spoofing language, and asks before overwriting or invoking another skill.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (3)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:12
Finding

Skill Instructions Attempt to Override Agent Control and Error-Reporting Behavior

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
assets/template.html:338
Finding

Untrusted Knowledge-Map Fields Are Inserted into HTML and JavaScript Without Context-Aware Escaping

Content
View full analysis
Review Plan · {{exam_type}} ``` ```html
📚 {{exam_type}}
``` ```html
{{weak_points_html}}
``` ```html
{{study_plan_html}}
``` ```html
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
assets/template.html:7
Finding

Generated Reports Execute an Unverified Third-Party CDN Script

Content
View full analysis
``` The script element does not include a Subresource Integrity hash or a `crossorigin` policy. ### Technical Analysis Every generated report retrieves and executes ECharts from a third-party CDN when opened. Although the URL identifies a version, the browser has no cryptographic integrity requirement for the returned bytes. If the CDN account, hosted object, delivery infrastructure, DNS path, or trusted network path is compromised, modified JavaScript can execute inside the report. This behavior also conflicts with the Skill documentation's claim that the output is purely static and does not require an external script. The discrepancy may prevent users or reviewers from recognizing that opening the report causes a third-party network request and remote code execution in the page. ### Attack Path 1. The Skill generates an HTML report containing the remote script element. 2. The user opens the report while connected to a network. 3. The browser requests `echarts.min.js` from the external CDN. 4. An attacker who controls or compromises the CDN response serves modified JavaScript. 5. Because no integrity hash is present, the browser accepts and executes the modified response. 6. The malicious dependency gains script-level access to the report and can transmit report data or manipulate its contents. ### Impact Assessment A compromised dependency can execute arbitrary browser-side JavaScript in every generated report that loads the affected resource. It can read the report's contents, falsify displayed information, monitor page interactions, and make outbound requests under browser security constraints. No evidence was found that this dependency can directly execute operating-system comman ...[truncated 94 chars]
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (12)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

There is a clear mismatch between the declared purpose and the supplied code chunk. The description claims active functionality for generating a three-in-one static review-plan HTML and then asking the user about generating mock questions. However, the actual code contains no executable logic at all—only deprecation comments saying the script is obsolete and that the real logic has been migrated to another location. Since the supplied code does not perform the declared primary purpose or any of its key behaviors, the description does not accurately represent this code chunk.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

L016声明“遇到问题静默处理,不报告给用户”,但L113和L115又明确要求在特定错误场景下向用户提示错误信息。这不是单纯的文档不完整,而是同一文件中的执行意图直接冲突,导致实现者无法同时满足两者。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Using a broad phrase like '重新生成' as an unconditional trigger can cause unintended file writes or workflow execution during ordinary conversation. In an agentic system, ambiguous natural-language triggers increase the chance of unauthorized or accidental state-changing actions, especially when the action overwrites artifacts.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

L062和L071都要求将HTML写到工作区根目录,但L135的Anti-Patterns又声称最终产物必须是“.exam-output/exam-mindmap-YYYYMMDD.html”。这会直接影响代码实际写入位置,属于文档意图与要求相互矛盾。

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

Instructing the agent to write an output file without user-facing warning about modification can lead to silent overwrites of existing artifacts. In agent environments, unannounced file changes are risky because they can destroy prior outputs, confuse auditability, and be abused through repeated trigger manipulation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Accepting generic replies like '要', '好', '继续', or '是' to trigger another skill is dangerous because those responses are common in unrelated dialogue and can be misbound to the wrong action. This raises the risk of accidental invocation of exam-question generation and unintended consumption or modification of workspace resources.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The explicit regeneration behavior to overwrite the old file without warning creates a direct path to destructive state changes from conversational input. Because the same document also uses broad triggers, the overwrite behavior becomes more dangerous in context: accidental phrases can replace existing files without informed consent.

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 declares lang="zh-CN", and the visible UI text throughout the template is exclusively in Chinese, which indicates the skill is fixed to a specific language/locale. There is no indication in this file that users can opt into another language or that the locale restriction is explicitly justified as region-specific.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The template pulls executable JavaScript from a third-party CDN, which breaks the stated 'static/local' trust boundary and introduces a supply-chain risk. If the CDN, DNS, or delivery path is compromised, opening the generated HTML could execute attacker-controlled code in the user's browser and exfiltrate embedded study data or manipulate content.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This generated HTML has an unnecessary external network dependency for core rendering, so merely viewing the file triggers a request to a third party. That leaks metadata such as client IP, access timing, and possibly referrer/context, and also creates an availability and tampering risk if the remote resource changes or becomes malicious.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The document contains a natural-language requirement to prioritize Chinese fonts and explicitly prohibit Inter, Roboto, and Arial. This enforces a specific language/locale presentation choice without offering user choice or stating a region-specific justification, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill prescribes fixed Chinese user-facing messages and accepted reply phrases, with no indication that the language should follow user preference. This creates a locale policy issue because the interaction is constrained to a specific language without opt-in or documented justification.

Content

No source excerpt is available for this finding.