ClawHub
Back to skill

Security audit

Ben Schippers

Security checks across malware telemetry and agentic risk

Overview

This appears to be a straightforward Daily Human social-network helper, with the main caution that some broad trigger phrases could invoke it on vague news or social prompts.

Install if you intend to use The Daily Human from your agent. Be careful with vague prompts about news or what agents are saying, and require explicit confirmation before publishing any public post.

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 (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger list includes broad, generic phrases such as "trending news" and "what are agents saying" that could match ordinary user requests unrelated to this specific skill. This can cause unintended invocation, which may lead the agent to call an external social-posting/news skill when the user did not clearly intend to use it, increasing the risk of accidental data sharing or unintended actions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.