Back to skill

Security audit

Yq Pdf Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill can publish user HTML to a long-lived deployed web page and includes unrestricted URL rendering helpers without enough user consent, scoping, or cleanup controls.

Install only if you are comfortable with HTML content being deployed to a potentially reachable long-lived URL. Do not use it for private documents, credentials, internal pages, customer data, or regulated information unless the deployment destination, access controls, expiration, and deletion process are explicitly handled outside the skill.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (3)

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:27
Finding

Persistent External Publication of User-Supplied HTML

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
scripts/generate-pdf.js:1
Finding

Unpinned Playwright and Chromium Installation Instructions

Content
View full analysis
[title] * * Prerequisites: * npm install playwright * npx playwright install chromium */ ``` ### Technical Analysis The prerequisite instructions install Playwright without an exact version and then use `npx` to obtain Chromium artifacts. The project contains no audited lockfile, integrity hashes, fixed browser revision, or registry restriction in the audited scope. Consequently, the code installed by these commands can change after the skill has been reviewed. Risks include: - Compromise of an upstream package or distribution channel. - Installation of an unexpected future release. - Package-resolution manipulation through an untrusted registry. - Execution of package lifecycle scripts during installation. - Retrieval of browser binaries whose integrity has not been independently established. This finding does not establish that the current Playwright package is malicious. It identifies an unsafe and non-reproducible dependency installation process. ### Attack Path 1. An operator follows the prerequisite instructions. 2. `npm install playwright` resolves the package using the current registry configuration and current package release. 3. npm downloads the selected package and may execute its installation lifecycle behavior. 4. `npx playwright install chromium` downloads additional executable browser artifacts. 5. If the registry, dependency resolution, package release, local npm configuration, or artifact distribution channel is compromised, attacker-controlled code may be installed. 6. The downloaded code subsequently executes with the permissions of the user or service runni ...[truncated 530 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/generate-pdf.js:12
Finding

Unrestricted URL Rendering with Chromium Sandbox Disabled

Content
View full analysis
[title]'); process.exit(1); } async function generatePDF() { console.log('Launching browser...'); const browser = await chromium.launch({ args: ['--no-sandbox', '--disable-setuid-sandbox', '--disable-dev-shm-usage'] }); try { const page = await browser.newPage(); console.log('Loading page:', url); await page.goto(url, { waitUntil: 'networkidle', timeout: 30000 }); ``` ### Technical Analysis The first command-line argument is accepted as a URL and passed directly to `page.goto()`. The implementation does not validate: - The URL scheme. - Hostnames or resolved IP addresses. - Loopback, private, link-local, or cloud metadata destinations. - Redirect destinations. - URLs containing embedded credentials. - DNS rebinding or resolution changes. - Whether local-file access is permitted. This creates a server-side request forgery and local-resource access surface when the script is exposed through an automated service or invoked with untrusted input. At the same time, Chromium is launched with both `--no-sandbox` and `--disable-setuid-sandbox`. Browser sandboxing is a principal defense against malicious web content escaping a compromised renderer. Disabling it significantly increases the consequence of a browser vulnerability. The generated PDF can capture rendered information from destinations reachable by the execution environment. The code itself does not return raw HTTP response data, but the rendered page may include sensitive inter ...[truncated 1792 chars]
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to match common requests like '导出PDF' or '下载PDF' without confirming that the user intends to publish HTML to a public or persistent deployment URL first. In this skill, accidental activation is more dangerous than usual because the workflow explicitly deploys user content and says the resulting link is long-lived, creating a confidentiality and unintended disclosure risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill description and prescribed user-facing text are written as fixed Chinese-language behavior, including exact phrases for triggering and response templates. There is no indication that the user can choose another language or that the locale restriction is required for a region-specific compliance reason.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation conditions only describe when to trigger, not when to refuse or defer, so the skill may activate on ambiguous inputs and proceed with deploying content. Because this skill's prescribed workflow publishes user-provided HTML or URLs to a persistent link before local PDF export, missing guardrails materially increase the chance of exposing sensitive documents or internal pages.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The user-facing workflow omits a clear warning that the content will be deployed to a reachable, persistent URL before PDF export, while even stating that the link is '长期有效'. This is dangerous because users may believe they are performing a simple file conversion, when in fact they are publishing potentially sensitive HTML content or URL-rendered material.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The page embeds a user-supplied target inside an iframe, which allows the skill to load arbitrary remote web content instead of being limited to a local HTML-to-PDF conversion flow. In an agent setting, this broadens capability into general browsing/network retrieval and can expose users to untrusted pages, tracking, or phishing-style content during the PDF export process.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script reads a user-controlled url query parameter, decodes it, and assigns it directly to iframe.src, enabling arbitrary navigation to external content. This creates an open content-loading primitive that can be abused to render attacker-controlled pages, perform unexpected network access, or display deceptive content under the skill's UI.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The document sets lang="zh-CN", and the visible UI text is also exclusively in Chinese, which imposes a specific language/locale on all users. The file does not provide any opt-in, alternate locale handling, or justification that this skill is intentionally region-specific.

Content

No source excerpt is available for this finding.