Back to skill

Security audit

Mortgage Marketing

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed mortgage marketing copy generator with no hidden execution or persistence, but users should review compliance-sensitive urgency claims and the unpinned Anthropic SDK dependency.

Before installing, be comfortable providing an Anthropic API key and installing an unpinned npm package. Review all generated mortgage copy for applicable advertising, fair-lending, NMLS, state, and platform requirements; do not rely on the skill's compliance flags as legal approval.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:13
Finding

Unpinned Third-Party npm Dependency

Content
View full analysis
Remediation
View remediation
" bins: [] ``` The placeholder must be replaced with a version that has been independently reviewed; selecting a version without review would not resolve the underlying supply-chain risk. ]]>
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly operationalizes loss/urgency framing for regulated mortgage marketing without any user-facing warning, safeguard, or limitation on manipulative use. In the context of financial decision-making, this can encourage coercive or misleading persuasion tactics that increase consumer harm and compliance risk, especially for vulnerable audiences such as first-time buyers or credit-challenged borrowers.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The input and output contracts, examples, platform guidance, and generated copy are all defined in English, but the skill does not state whether other languages/locales are supported or give the user a choice. Under the policy, forcing a specific language without opt-in can be a natural-language policy issue unless the locale limitation is explicitly documented and justified.

Content

No source excerpt is available for this finding.