Circle 1

• Outcome: Review
• Latest audit: May 29, 2026 at 9:37 PM UTC
• Version:
  1.0.4

Overview

The skill appears to support Circle API work, but it exposes broad write and delete access without clear guardrails, so it should be reviewed before installation.

Install only if you trust the publisher and are comfortable giving the skill Circle API authority. Use least-privilege or sandbox credentials first, avoid production tenant keys until reviewed, and require explicit confirmation before any create, update, or delete operation.

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: 91% confidence
• Finding: The skill documents a generic proxy mechanism that supports arbitrary API paths and destructive HTTP methods like POST, PUT, PATCH, and DELETE without any embedded warning, approval gate, or confirmation requirement. In an agent setting, this increases the chance that the model could perform unintended state-changing operations against a live Circle tenant, especially when actions are not well constrained.

VirusTotal

63/63 vendors flagged this skill as clean.