ClawHub
Back to skill

Security audit

Halo Cli

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Halo CLI routing skill; it points agents to the right Halo command area and does not include hidden execution, persistence, or exfiltration behavior.

Install this as a general Halo CLI router. Because it can route to authenticated and destructive Halo operations, review commands involving `--profile` or `--force` carefully and make sure the intended Halo site/profile is selected before changing posts, plugins, themes, backups, comments, or notifications.

A.I.G

Vulnerability Patterns
  • 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
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation description is broad enough to match many generic requests involving Halo CLI, including mixed or underspecified tasks. That can cause this routing skill to activate when a more specific skill should handle the request, increasing the chance of incorrect command selection, overbroad tool usage, or unintended access to authenticated/destructive operations exposed by referenced sub-skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.