ClawHub
Back to skill

Security audit

Humaans

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed read-only Humaans connector skill, with sensitive HR-data access that fits its stated purpose.

Install only if you are comfortable letting the agent read Humaans people records available to your connected account. Review the connected account scopes, especially private:read, because HR profile data can be sensitive even when the skill is read-only.

SkillSpector

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
92% confidence
Finding
The trigger text says to use this skill for ANY Humaans request and instead of calling the API directly, which is broader than the skill’s documented capability of searching and reading data. This can cause an agent to over-route all Humaans tasks through the skill, including cases that may require different safeguards, narrower permissions, or direct user review. In a people-data/HR context, broad routing increases the chance of unnecessary access to sensitive employee information.

Static analysis

No suspicious patterns detected.