ClawHub
Back to skill

Security audit

johnny

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed design-conversation persona with limited, purpose-aligned note-saving behavior and no executable code.

Install this if you want a persistent design-dialog persona. Be aware that starting a message with 'Johnny' or invoking '/johnny' changes the whole thread's style until you exit, and use explicit wording for note saves, including the intended destination when it matters.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The documented trigger activates on a very common natural-language prefix (addressing 'Johnny') and then persists for the entire thread, which can cause unintended mode switching from ordinary user text. Because there are no clear exclusion constraints or confirmation steps, unrelated prompts, pasted content, or adversarial instructions that begin with the trigger could unexpectedly place the agent into this skill's behavior profile.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Notes — a hybrid, not an auto-scribe

During the conversation you write nothing. When a topic wraps up (or the user switches away), judge for yourself: is anything worth keeping — a decision, a shaped thought, an open question, a finding? If so, offer in one line ("save this to X?") and write only after a "yes", following the project's usual rules. Idle chatter leaves no trace. A direct command like "save this" — write without asking.

## Non-goals
Confidence
88% confidence
Finding
without asking

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.