AI Skill Maintainer (EN)

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:38 PM UTC
• Version:
  1.1.0-en2

Overview

This appears to be a code-maintenance skill with broad activation wording, but no evidence of hidden behavior, persistence, credential handling, or unsafe installation.

Before installing, treat this as a repo-maintenance helper: confirm the exact target repository and task, review proposed code and dependency changes, run tests, and avoid giving it credentials or account access unless a specific maintenance action clearly requires them.

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: 86% confidence
• Finding: The skill advertises very broad trigger phrases for maintenance actions such as updates, bug fixes, dependency upgrades, and security patches without clear scoping or exclusion boundaries. In an agent ecosystem, this can cause the skill to activate on generic requests and perform sensitive maintenance workflows or recommend privileged actions when a more specific skill or human review should be required.

VirusTotal

64/64 vendors flagged this skill as clean.