Secure Code Warrior

• Outcome: Review
• Latest audit: May 29, 2026 at 9:37 PM UTC
• Version:
  1.0.2

Overview

This appears to be a real Secure Code Warrior integration, but it gives broad authenticated control over an external service without clear safety limits.

Review before installing. Use a low-privilege Membrane and Secure Code Warrior account, verify OAuth or account scopes, prefer prebuilt read-only actions where possible, and require explicit confirmation before modifying users, roles, permissions, enrollments, settings, subscriptions, transactions, or other organization data.

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

Medium

• Confidence: 88% confidence
• Finding: The skill description is overly broad ('Manage data, records, and automate workflows'), which can cause an agent to invoke this integration for generic requests that are not clearly about Secure Code Warrior. Because the skill supports authenticated actions against an external service, over-triggering increases the chance of unintended data access or state-changing operations in the wrong context.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The proxy-request section instructs the agent how to send arbitrary authenticated HTTP requests, including POST, PUT, PATCH, and DELETE, but does not warn that these can modify or delete remote data. In a skill that manages external SaaS resources, this omission makes unintended destructive operations more likely, especially if an agent improvises with direct API calls instead of safer prebuilt actions.

VirusTotal

63/63 vendors flagged this skill as clean.