ClawHub
Back to skill

Security audit

Humanitix

Security checks for vulnerabilities and agentic risk

Overview

The skill mainly reads Humanitix data, but its first-time setup includes unverified internet installer commands that could run arbitrary local code.

Review the setup instructions before installing. Use an already installed trusted oo CLI where possible, or download and verify the installer through an official, versioned, checksum- or signature-backed channel instead of piping it directly to a shell.

A.I.G

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:57
Finding

Unverified Remote Installer Download and Immediate Execution

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into the shell (curl ... | bash). This is dangerous because it executes unverified code from the network immediately; if the host, transport, CDN, or script is compromised, the agent could run arbitrary commands with the user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file contains invocation guidance that is very broad and lacks clear scope boundaries. Phrases like "ANY Humanitix request" and "Whenever a task involves Humanitix" can overlap with many ordinary requests involving Humanitix, without specifying exclusions or narrower trigger conditions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.