Security audit

Bazi Qimen

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a disclosed Bazi and Qi Men calculation aid with no evidence of hidden access, persistence, network use, or destructive behavior.

Before installing, consider that the skill may ask for birth date, birth time, and gender for chart calculations, and its results are traditional-cultural reference material rather than advice for major decisions. When a request is ambiguous, ask the agent to confirm whether you want Bazi, Qi Men, or both.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (3)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The code is clearly aligned with part of the description: it calculates Ba Zi/Four Pillars astrology data and related traditional metaphysics attributes. However, the declared purpose says the skill covers both Bazi and Qi Men Dun Jia chart calculation and interpretation. In this code chunk, there is no Qi Men Dun Jia logic at all—no corresponding data structures, chart generation, palaces, doors, stars, stems arrangement, or interpretation routines. The code also mainly performs deterministic Ba Zi computations and returns structured results, with only a brief note; it does not meaningfully implement interpretive reasoning or any cognitive science/data-analysis layer suggested by the description. Therefore the description overstates the implemented functionality in a material way.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger list contains broad terms like 'interpretation', 'pattern', and 'chart calculation' that may match unrelated user requests and invoke the skill unintentionally. In an agent system, overbroad activation can cause inappropriate tool use, irrelevant metaphysical advice, and accidental processing of sensitive personal data such as birth date, time, and gender.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: When user intent is unclear, the skill defaults to calculating Bazi first and then supplementing with Qi Men, which expands scope without clear consent. This can lead to unnecessary execution paths, overcollection of sensitive data, and delivery of unsolicited divination-style outputs in contexts where the user did not ask for them.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.