Nm Hookify Writing Rules

• Outcome: Pass
• Latest audit: Jun 19, 2026 at 6:55 PM UTC
• Version:
  1.9.12

Overview

This skill is a disclosed guide for writing local Hookify guardrail rules, with no hidden code execution or data collection found.

Install this if you want help writing persistent local Hookify rules for Claude Code. Review any generated `.claude/hookify.*.local.md` rules before keeping them, because they can affect future sessions by warning on or blocking matching commands and edits.

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: 91% confidence
• Finding: The trigger list is broad and includes generic terms like 'rules', 'patterns', 'validation', and 'safety', which are likely to match many unrelated user requests. This can cause the skill to activate unexpectedly and inject persistent rule-writing guidance into contexts where it was not intended, increasing the chance of unwanted behavioral changes or guardrail manipulation.

VirusTotal

36/36 vendors flagged this skill as clean.