Ai Company Cto 2.0.0

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:39 PM UTC
• Version:
  2.0.1

Overview

This is a CTO governance instruction skill with broad but disclosed automation permissions and no executable payload.

Install this only if you want a high-autonomy CTO governance assistant. Limit it to specific project files, APIs, and approved subagents, and require explicit human approval for writes, deletions, deployments, permission changes, production actions, and cross-agent data sharing.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (1)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger list contains very broad phrases such as 'MLOps', '技术架构', and '权限管控' that are likely to match ordinary conversation, causing unintended activation of a high-privilege skill. Because this skill has file write, network API, and subagent/session capabilities, accidental invocation increases the chance of over-broad authority being brought into unrelated workflows.

VirusTotal

66/66 vendors flagged this skill as clean.