ClawHub
Back to skill

Security audit

Generate Mortgage Broker Team Client Education Handout

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple mortgage-client education handout generator with no hidden execution, persistence, or data access behavior found.

Review generated mortgage education content before sharing with clients, especially for compliance and financial accuracy. The skill appears low-risk, but its Bash permission is broader than needed for ordinary content drafting.

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
95% confidence
Finding

The description is visibly truncated ('Use when handling client education work for...'), which leaves the skill's activation scope unclear. Ambiguous scope can cause the agent to invoke this skill in unintended contexts, increasing the chance of misapplication, poor routing, or generation of regulated financial content without the right safeguards or review.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.