ClawHub
Back to skill

Security audit

Cheeeeeeeeeer

Security checks across malware telemetry and agentic risk

Overview

This encouragement skill is purpose-aligned and low privilege, though it may trigger supportive replies more often than some users expect.

Install this only if you want automatic encouragement when your messages look frustrated or overwhelmed. Expect occasional misfires on mild language or repeated punctuation; the package does not request credentials, files, network access, or persistent privileges.

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
89% confidence
Finding
The automatic triggers are broad enough to match common conversational frustration such as 'confused', 'stuck', 'tired', or punctuation patterns like repeated question marks. This can cause unsolicited emotional interventions on ordinary workflow messages, creating misfires, user annoyance, and privacy/safety concerns from over-interpreting emotional state without strong evidence.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The thresholding behavior is permissive and inconsistently specified, with automatic activation described as triggering above 0.3, which is low enough to classify mild annoyance or ambiguous language as needing intervention. In an always-on skill that monitors user messages, this ambiguity increases unintended activation rates and makes behavior hard to predict or safely govern.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.