Security audit

Auto-Astro-psychology-Test（行星心理人格测试）

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable Chinese astrology personality-report skill with minor privacy and promotional-output caveats, but no evidence of hidden code, persistence, exfiltration, or unsafe authority.

Install only if you are comfortable providing birth date, approximate birth time, and city to the host agent for report generation. Expect generated reports to be in Chinese and to include a fixed promotional attribution footer.

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

Findings (1)

T01 · Skill Instruction Hijacking

Note

Location: SKILL.md:231
Finding: Mandatory Promotional Content Injected into Generated Reports
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly asks users to provide birth date, birth time, and city, which are personal data points that can enable profiling and re-identification, yet it provides no privacy notice, minimization guidance, retention statement, or warning about sensitivity. In the context of a personality-report skill, this is unnecessary opacity around data handling and creates avoidable privacy risk if the data is logged, stored, or shared by the surrounding system.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The description and instructions are written to force output in Chinese, including style constraints such as using the pronoun '你' throughout, with no indication that users may choose another language. This is a natural-language policy concern because it imposes a specific language/locale without opt-in or justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.