Security audit

起名大师

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese naming skill with some scope and inclusivity limitations, but no hidden execution, persistence, credential access, or data exfiltration behavior.

Install only if you want Chinese-style naming analysis. Be aware that it may ask for birth date/time and binary gender to perform traditional 八字 and 五行 analysis; provide only what you are comfortable sharing, and treat the metaphysical scoring as cultural reference rather than fact.

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 (5)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill is explicitly specialized for Chinese naming but does not clearly disclose that limitation or offer a language/locale fallback, so users may be steered into a Chinese-only framework even when asking in another language or for non-Chinese naming conventions. In context this is not overtly malicious, but it can lead to inappropriate outputs, cultural mismatch, and needless requests for sensitive birth details under assumptions the user did not intend.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are broad enough to capture generic naming-related requests such as '英文名' or '笔名', which may route users into a highly specialized Chinese metaphysics naming workflow that is not appropriate for their intent. This is primarily a scope/dispatch safety issue: misrouting can cause irrelevant advice, unnecessary collection of personal birth data, and degraded user experience rather than direct code-execution or data-exfiltration harm.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The file hard-codes gendered naming categories such as '男用' and '女用' without indicating that these labels are optional, culturally contextual, or user-selectable. In a naming skill, this can lead the agent to make exclusionary or stereotyping recommendations, especially for users who want gender-neutral names or do not identify within binary categories.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: Line L073 states '男楚辞，女诗经' as a general naming rule, and later sections provide separate '男用辈字' and '女用辈字' lists. This natural-language guidance imposes gendered naming conventions rather than presenting them as optional cultural traditions, which can violate policy expectations around inclusive user choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. This markdown content presents all instructions and guidance only in Chinese, with no indication of user opt-in, alternative language availability, or justification for restricting the skill to a Chinese-reading audience.
Content: No source excerpt is available for this finding.