Security audit

bazi-fortune-analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only BaZi fortune-reading skill that asks for personal birth details for its stated purpose, with no evidence of code execution, persistence, or data exfiltration.

Install only if you are comfortable sharing birth details for fortune analysis. Treat the output as cultural or entertainment guidance, not as medical, financial, relationship, or life-planning advice.

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
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 (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger list includes very broad, common terms such as 'fortune' and 'astrology', which can cause the skill to activate in contexts the user did not intend. Unintended invocation can lead to accidental collection of sensitive birth data and delivery of high-confidence personal advice in inappropriate conversations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The workflow instructs the skill to collect full birth date, time, location, and gender, which together form highly sensitive personal profile data, but the skill does not present a clear upfront privacy warning or consent step before collection. This increases the risk of oversharing, especially if the skill is triggered unintentionally or used in shared environments.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 73% confidence
Finding: All user-facing instructions and outputs are specified in Chinese, but the skill does not state whether this is a required locale or offer users a language option. Under the language/locale policy, forcing a specific language without opt-in can be a natural-language policy issue unless the restriction is explicitly justified.
Content: No source excerpt is available for this finding.