Mysteel_BidSupply

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:28 PM UTC
• Version:
  1.0.0

Overview

This skill does what it says by querying Mysteel steel supply, demand, and bidding data, but users should treat its saved API key as a plaintext local secret.

Install only if you are comfortable sending steel procurement, supply, demand, and bidding searches to Mysteel. Use a dedicated or low-privilege Mysteel API key if possible, keep references/api_key.md out of shared or synced workspaces, delete it when no longer needed, and rotate the key if the workspace may have been exposed.

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
• 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

Findings (4)

Context-Inappropriate Capability

Medium

• Confidence: 90% confidence
• Finding: The script can persist an API key to a local markdown file under the skill directory, creating a plaintext secret-at-rest risk. This is not necessary for the core query functionality and increases exposure to accidental disclosure via local file reads, packaging, backup, source control inclusion, or other skills/processes accessing the workspace.

Vague Triggers

Medium

• Confidence: 80% confidence
• Finding: The description and activation conditions are broad enough to match common procurement, sales, and project-discovery queries, which increases the chance the skill is invoked when not specifically intended. Over-broad triggering can route unrelated business requests into a skill that performs network calls and uses stored credentials, expanding the attack surface and risking unnecessary data exposure.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill instructs users to save an API key into a local markdown file without any warning about plaintext secret storage, access controls, or rotation. Storing credentials in an easily readable file creates a realistic risk of credential disclosure through local file access, logs, backups, or accidental sharing, which could lead to unauthorized API use.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The script writes the API key in plaintext to a predictable local file without any warning, access control, or permission hardening. On shared systems or in repos/workspaces with broad access, this can expose reusable credentials to other local users, backup systems, or accidental commits.

VirusTotal

64/64 vendors flagged this skill as clean.