mkts Market Data

• Outcome: Review
• Latest audit: May 28, 2026, 8:41 AM
• Version:
  1.0.11

Overview

This market-data skill appears coherent, but it can create, update, and delete portfolio, journal, and watchlist data without clear confirmation guidance.

Install only if you are comfortable sending market queries and any portfolio, journal, or watchlist content to mkts.io. Treat all write, delete, and clear commands as state-changing: review affected records first, confirm exact IDs or counts with the user, and keep MKTS_API_KEY private.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill documents destructive DELETE operations for portfolio holdings and clearing all holdings/watchlists, but provides no instruction to require explicit user confirmation, verify scope, or warn about irreversible data loss. In an agent setting, this increases the risk that a misunderstood prompt or prompt-injected workflow triggers account-modifying actions against real user data.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The journal and watchlist sections expose write and delete operations involving potentially sensitive personal trading notes and curated lists, but omit privacy warnings, confirmation steps, or retention expectations. In an autonomous-agent context, this can lead to unintended disclosure to the external service and accidental loss of user-created data.

VirusTotal

66/66 vendors flagged this skill as clean.