Mintsoft

• Outcome: Pass
• Latest audit: Jun 19, 2026 at 8:44 AM UTC
• Version:
  1.0.0

Overview

This is a disclosed Mintsoft API query wrapper, with an optional local token cache that users should treat as sensitive.

Prefer using a pre-issued MINTSOFT_API_KEY or environment variables instead of passing passwords on the command line. Install only if you are comfortable letting the skill read Mintsoft warehouse and order data and cache a temporary API key locally.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Description-Behavior Mismatch

Medium

• Confidence: 92% confidence
• Finding: The manifest markets the skill as using only a single API key, while the documentation expands scope to username/password login and cached token reuse. This is dangerous because it undermines informed consent and may lead operators to expose primary account credentials where they expected only a scoped API secret to be used.

Description-Behavior Mismatch

Medium

• Confidence: 95% confidence
• Finding: The skill metadata says it is a single API-key wrapper, but the code also supports username/password authentication and exchanges those credentials for a cached API key on disk. This expands the credential surface beyond the declared purpose, increasing the chance that a caller supplies higher-value credentials than expected and that those secrets are persisted locally.

Context-Inappropriate Capability

Medium

• Confidence: 94% confidence
• Finding: The code reads username and password from flags or environment variables, sends them to the remote Auth endpoint, and caches the returned token locally. For an API-wrapper skill advertised as using one API key, this is an unnecessary credential expansion that can capture and persist more sensitive account credentials than users expect.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: Accepting passwords via command-line flags can expose credentials through shell history, process listings, job-control logs, and agent telemetry. In multi-user or monitored environments, another local user or logging system may recover the password even if the API call itself uses HTTPS.

VirusTotal

64/64 vendors flagged this skill as clean.