ClawHub
Back to skill

Security audit

Catholic AI Ethics

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill provides Catholic AI ethics guidance with public API examples; the main caution is an optional unpinned npm MCP command.

Before using the optional MCP command, review the package source or pin a known version. If you only use the curl examples or read the markdown content, the skill does not request accounts, credentials, or local data access.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The skill instructs users to run npx -y mcp-magnifica-family without pinning a specific package version or integrity-verified source. That allows whatever version is current on the npm registry at execution time to be installed and run, creating a supply-chain risk if the package is later compromised, renamed, or updated with malicious code.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.