myskill

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 11:50 PM UTC
• Version: 1.0.1

Overview

This is a documentation-only exec configuration reference with caution-worthy defaults, but it does not contain hidden code, automatic execution, persistence, or exfiltration behavior.

Before installing, treat this as low-level exec reference material rather than a task-specific skill. Use host, gateway, node, elevated, and sandbox-off settings only when you intentionally want command execution outside a contained sandbox and understand the approval policy in effect.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

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 content is purely low-level exec configuration documentation and does not define when the skill should be invoked, what user intents it serves, or what constraints apply. In an agent setting, unclear activation scope can cause the skill to be selected in overly broad contexts, increasing the chance of unintended command execution or unsafe host access pathways.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The documentation explicitly states that sandboxing is off by default while also describing gateway/node host execution, approvals, elevation, and execution policy controls, but it does not foreground the security consequences to the user. This can normalize dangerous defaults and lead operators or downstream agents to run commands on the host with access to real system state, risking data loss, credential exposure, or system compromise if commands are misused or attacker-influenced.