DKnownAI Guard

• Outcome: Pass
• Latest audit: Jun 15, 2026 at 6:09 AM UTC
• Version:
  1.0.2

Overview

This skill is a coherent API wrapper for checking user-selected text with DKnownAI Guard, with one credential-handling caution.

Install only if you are comfortable sending checked text to DKnownAI Guard. Prefer entering the API key through a platform secret store or environment variable instead of pasting it into chat; if you do paste it, treat it as exposed to the current agent/session and rotate it if needed.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The setup flow explicitly recommends that users send their API key through chat so the agent can write it to a local config file, but it does not clearly warn that secrets exposed in chat may be visible to the agent, platform, logs, or other retention systems. This increases the chance of credential disclosure through normal use rather than through a technical exploit.

VirusTotal

65/65 vendors flagged this skill as clean.