Back to skill

Security audit

Mystical Divination Toolkit

Security checks for vulnerabilities and agentic risk

Overview

This is a static divination reference skill with no code execution, persistence, network access, or hidden authority.

Install only if you want entertainment-style divination and numerology guidance. Avoid relying on readings for high-stakes financial, legal, medical, or safety decisions, and do not share a full birth date unless you are comfortable using it for the immediate numerology calculation.

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
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs the agent to ask for a full birth date, which is personal data, without any disclosure about why it is collected, how it will be used, whether it will be retained, or whether a less sensitive alternative is available. This creates privacy risk and can normalize unnecessary collection of sensitive profile data in an entertainment-oriented skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill claims support for 'Natural language triggers' but does not define a bounded invocation set, exclusions, or disambiguation rules. In agent environments, overly broad trigger wording can cause unintended activation from ordinary conversation, leading the agent to perform divination guidance when it was not explicitly requested and increasing the risk of prompt-routing confusion or misuse.

Content

No source excerpt is available for this finding.