ClawHub
Back to skill

Security audit

Agent Errantry Alignment

Security checks for vulnerabilities and agentic risk

Overview

This is a conceptual AI workflow metaphor skill with broad invocation language but no executable code, hidden actions, persistence, credential handling, or data access.

Installers should understand that this skill may be invoked for fairly general AI workflow or agent-design conversations and may steer the discussion into a Young Wizards metaphor. It does not appear to perform actions on its own or request sensitive access.

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
Confidence
91% confidence
Finding
The skill description is broadly scoped to common activities like designing workflows, explaining AI concepts, debugging agent behavior, and framing constraints. That makes it likely to be invoked in many ordinary requests, increasing the chance it inappropriately steers conversations or overrides more suitable specialized skills, even though the content itself is largely conceptual and safety-oriented.

Static analysis

No suspicious patterns detected.