ClawHub
Back to skill

Security audit

Deed

Security checks for vulnerabilities and agentic risk

Overview

This skill is only a Markdown instruction file, but it asks agents to handle high-impact property-title, deed, lien, and dispute-resolution decisions without clear user approval or scope limits.

Review carefully before installing. Use this only as a conceptual or drafting aid unless it is revised to require explicit human approval, verified legal data sources, jurisdiction-specific limits, and refusal rules for real deed transfers, lien determinations, escrow actions, or ownership-dispute decisions.

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
90% confidence
Finding
The skill metadata and description define a broad, high-authority asset ownership protocol but provide no explicit activation criteria, scope limits, or refusal conditions. In an agentic system, this ambiguity can cause the skill to trigger in inappropriate contexts involving legal, financial, or property-transfer decisions, increasing the risk of unauthorized or unsound actions based on incomplete verification.

Static analysis

No suspicious patterns detected.