Back to skill

Security audit

Nyan Parlor: Tarot, I Ching & BaZi

Security checks for vulnerabilities and agentic risk

Overview

The skill fits its stated purpose, though online readings share supplied questions or birth details with tarotoper.com.

Use online readings only with information you are comfortable sharing with tarotoper.com; its data retention practices are not established by this package. Local tarot and I Ching draws avoid submitting reading inputs, but require correcting the documented script paths. BaZi requires the external service.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The skill directs use of a third-party service without warning that personal reading inputs will be transmitted.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The skill directs the agent to send reading questions and birth details to an external MCP service without requiring disclosure or informed user approval. These inputs can reveal identifying information or sensitive relationship, health, and financial concerns, while the service's retention and handling practices are unspecified. The transmission serves the skill's stated purpose rather than demonstrating malicious exfiltration, but that legitimate purpose does not eliminate the privacy risk.

Content

No source excerpt is available for this finding.