Ask Lenny

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:24 PM UTC
• Version:
  1.0.4

Overview

This is a disclosed local archive-search skill with minor setup and activation cautions, not evidence of harmful behavior.

Install this if you are comfortable running a setup script that downloads public archive data from GitHub and stores a local searchable index. Prefer explicit invocations like '@lenny' to avoid accidental activation, and consider pinning or reviewing the downloaded data source in stricter environments.

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: 87% confidence
• Finding: The README defines trigger phrases including natural-language forms like 'ask lenny <question>' and 'what does lenny think about <topic>', which can overlap with normal conversation rather than an explicit tool invocation. In an agent environment, broad triggers can cause unintended activation, leading the skill to intercept unrelated user requests and influence responses without clear user intent.

VirusTotal

65/65 vendors flagged this skill as clean.