Back to skill

Security audit

catholic-family-soul

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed markdown-only skill for generating a family-oriented Catholic system prompt, with an optional MCP install path that users should treat with normal package-install caution.

Before installing, review the generated SOUL.md because it is meant to shape future assistant behavior for your family. Prefer the curl/browser workflow if you only need the prompt text; if using the MCP option, verify the package and consider pinning a trusted version before running npx.

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
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The markdown explicitly states that the lang parameter defaults to en, which imposes a specific language when the user does not actively choose one. Under the policy, locale or language constraints should be offered as a choice or require opt-in unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

The skill instructs users to execute an unpinned NPX package directly from the registry, which can cause arbitrary code execution if the package is later compromised, typo-squatted, or updated with malicious behavior. Because this is presented as a normal installation path for an MCP server, users may run it with little scrutiny, increasing supply-chain risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.