Back to skill

Security audit

Ditiansui Publish

Security checks for vulnerabilities and agentic risk

Overview

This is a simple BaZi fortune-analysis prompt skill with no code, hidden behavior, persistence, or elevated access.

Before installing, understand that this skill may ask for birth date and time and will provide astrology-style personal guidance. Avoid using it as the sole basis for important financial, medical, legal, or relationship decisions.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill is framed around Chinese BaZi destiny analysis and repeatedly centers Chinese-specific concepts and terminology, but the description does not state that users can choose language or locale preferences. Under the policy rule for natural-language violations, a skill should not implicitly force a specific language/locale context without opt-in or a clearly documented regional justification.

Content

No source excerpt is available for this finding.