ClawHub
Back to skill

Security audit

Flight Lines

Security checks for vulnerabilities and agentic risk

Overview

This is a single Markdown reasoning skill for creative cross-domain problem solving, with no code, install hooks, persistence, or data access.

Use this as a brainstorming aid for low-risk, exploratory problems. For medical, legal, financial, security, or other high-stakes decisions, prefer domain-standard guidance or expert-backed methods rather than speculative cross-domain composition.

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
94% confidence
Finding

The skill says to use the approach whenever standard methods feel 'exhausted' or when a problem 'wants a different kind of solution,' while only vaguely excluding cases where stakes require proven approaches. That broad activation scope can cause an agent to apply speculative, cross-domain reasoning to tasks outside its competence or to safety-sensitive situations without clear boundaries, increasing the chance of hallucinated, inappropriate, or risky guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.