ClawHub
Back to skill

Security audit

Founder Wisdom

Security checks across malware telemetry and agentic risk

Overview

This is a text-only startup advice skill with broad but disclosed activation, and I found no hidden execution, data access, persistence, or exfiltration behavior.

Install only if you want an opinionated, venture-backed startup perspective to influence founder and operator advice. Treat its legal, tax, finance, hiring, and governance suggestions as pattern-matching prompts rather than professional advice, and ask the assistant to narrow or skip the skill when you want neutral, jurisdiction-specific, or expert-reviewed guidance.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The README describes very broad triggering conditions for founder-stage and startup-related questions, which can cause the skill to activate for many loosely related conversations. While this is not a classic exploit primitive, over-broad invocation can inappropriately steer responses toward the skill's opinionated corpus, increasing the chance of irrelevant, biased, or overconfident advice being surfaced when another skill or the base model would be more appropriate.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill is configured to trigger on very broad conversational patterns such as generic founder uncertainty or second-hand advisory contexts, which can cause over-invocation and unsolicited guidance in conversations that did not clearly request this skill. In a safety-sensitive assistant environment, broad activation increases the chance of irrelevant, overconfident, or context-mismatched advice being surfaced, especially because the skill is explicitly opinionated and "not neutral or comprehensive."

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.