PDF to Markdown - Extract Text, Tables, Formulas from PDF

• Outcome: Pass
• Latest audit: May 29, 2026, 8:28 PM
• Version:
  1.0.4

Overview

This is a straightforward PDF-to-Markdown skill that discloses its third-party MinerU processing, but users should avoid sending sensitive PDFs unless that is acceptable.

Install only if you are comfortable adding the mineru-open-api CLI and sending selected PDFs or PDF URLs to MinerU for online processing. Do not use it for confidential, regulated, or highly sensitive documents unless third-party processing is allowed.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (1)

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The skill's activation guidance uses very broad verbs like "read," "extract," "convert," "parse," "summarize," and "analyze" a PDF, which can cause the agent to invoke this external-processing skill for many ordinary document tasks without sufficiently specific user intent. Because the tool sends documents or URLs to a third-party API, overbroad triggering increases the chance of unintended data exfiltration or use on sensitive PDFs when a safer local or non-upload workflow would have been more appropriate.

VirusTotal

66/66 vendors flagged this skill as clean.