Nutrient Document Processing (Universal Agent Skill)

• Outcome: Pass
• Latest audit: May 28, 2026, 10:49 AM
• Version:
  1.1.2

Overview

This skill transparently helps process user-selected documents through Nutrient’s cloud API, with no artifact-backed evidence of hidden or malicious behavior.

Install this only if you are comfortable sending selected documents to Nutrient’s API. Use a dedicated API key if possible, protect any MCP config file containing that key, set SANDBOX_PATH to a narrow work directory, and double-check which files are being processed before OCR, extraction, redaction, signing, or batch operations.

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: 91% confidence
• Finding: The activation keywords are very broad, including generic terms like 'PDF', 'document', 'extract', and 'sign', which could cause this skill to trigger on many unrelated user requests. That increases the chance an agent invokes document-uploading or external-processing guidance unexpectedly, creating unnecessary exposure of files or credentials to a third-party service.

VirusTotal

62/62 vendors flagged this skill as clean.