Unix A History And A Memoir

• Outcome: Review
• Latest audit: Jun 7, 2026 at 11:14 PM UTC
• Version:
  1.0.0

Overview

This is mostly a text-only engineering-culture skill, but it includes actionable advice to make unofficial paperwork look official, which users should review before installing.

Install only if you are comfortable with a broad, branded book-guidance skill. Avoid following any advice that suggests making unofficial processes appear official; use it as historical inspiration, not as authorization to bypass workplace approvals or governance.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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 (3)

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The skill defines trigger conditions using broad, ambiguous phrases and keyword mentions, which can cause the skill to activate in contexts where the user did not intend to invoke it. This creates prompt-routing confusion and increases the chance of irrelevant or policy-conflicting behavior being injected into unrelated conversations.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: Telling the AI to appear whenever it 'senses this book could help' sets an undefined invocation boundary and encourages unsolicited activation. In a multi-skill or general assistant environment, this can lead to inappropriate takeovers of conversations, reduced user control, and accidental instruction interference.

Natural-Language Policy Violations

High

• Confidence: 97% confidence
• Finding: The skill explicitly advises users to invent a process and 'make it look official,' which normalizes deception, policy circumvention, and unauthorized procurement or access. In an executable guidance context, this can directly enable fraud, social engineering, or bypassing internal approval controls, and the historical anecdote does not sufficiently neutralize the actionable instruction.

VirusTotal

64/64 vendors flagged this skill as clean.