Secure Workspace

• Outcome: Pass
• Latest audit: Jun 8, 2026 at 11:15 PM UTC
• Version:
  1.0.0

Overview

This is a local age-based secret encryption helper with expected sensitive-secret handling and no evidence of exfiltration or hidden execution.

Install only if you are comfortable managing local secret files and an age private key. Avoid sourcing decrypted secrets in long-lived shells unless needed, clear environment variables afterward, and protect the private key because anyone with it can decrypt the stored secrets.

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 (2)

Vague Triggers

Low

• Confidence: 83% confidence
• Finding: The usage section gives direct execution steps but does not define when the skill should or should not be invoked. In agent contexts, missing trigger constraints can cause the skill to run in broader situations than intended, increasing the chance of unnecessary secret handling or shell execution.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The documented decryption flow uses `source <(bash scripts/secure/decrypt.sh ...)`, which injects decrypted secret material directly into the current shell environment. Without a clear warning, users or agents may expose secrets to shell history, process inspection, logs, child processes, or subsequent commands in the same session.

VirusTotal

64/64 vendors flagged this skill as clean.