Yq Pdf Generator

• Outcome: Review
• Latest audit: May 31, 2026, 1:22 AM
• Version:
  1.0.0

Overview

This skill is not clearly malicious, but it can publish user-provided HTML or URLs to a long-lived hosted page without enough consent or scoping.

Install only if you are comfortable with HTML or URL content being deployed to a persistent hosted link. Do not use it for confidential documents, private URLs, internal pages, credentials, customer data, or drafts unless you add an explicit confirmation and cleanup/access-control process.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

• Confidence: 79% confidence
• Finding: Overly broad trigger phrases can cause the skill to activate on ordinary conversation and process content or URLs the user did not intend to publish. In this skill's context, activation can lead to deployment of arbitrary HTML to a long-lived public URL, so accidental triggering increases the chance of unintended data exposure rather than being a mere UX issue.

Vague Triggers

Medium

• Confidence: 82% confidence
• Finding: The activation rules specify when to trigger but not when to avoid triggering, which can cause the skill to run in ambiguous contexts. Because the workflow deploys user-provided HTML/URLs and returns a persistent link, mistaken activation can expose sensitive drafts, internal pages, or private documents to unintended audiences.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The page accepts an arbitrary `url` query parameter and assigns it directly to the iframe `src`, allowing untrusted external or local content to be embedded without validation, restriction, or user warning. In a PDF-generation skill, this can be abused to load phishing pages, sensitive internal resources, or hostile content that manipulates what the user prints or saves, increasing SSRF-like and clickjacking-style risk depending on the runtime environment.

VirusTotal

65/65 vendors flagged this skill as clean.