Security audit

超级个体 90 天行动计划

Security checks for vulnerabilities and agentic risk

Overview

This skill creates a Chinese 90-day personal action plan and shows no evidence of hidden code, exfiltration, destructive behavior, or privilege escalation.

Install this if you want a Chinese-language 90-day action-planning assistant. Before using it, be aware that it may save a local Markdown plan containing your name, goals, constraints, and reflections; ask the agent to show the plan inline or confirm the filename first if that matters to you.

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 (5)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The manifest description contains vague trigger-oriented wording like '90天计划', '行动方案', and '从现在开始' without scope constraints, which can cause the platform to associate the skill with broad, common requests. This raises the risk of accidental invocation and misrouting, especially in systems that use descriptions for discovery or matching.

Vague Triggers

Medium

Confidence: 97% confidence
Finding: The trigger phrases include highly generic language such as '行动方案', '给我制定计划', and '不知道从哪里开始', which can appear in ordinary conversations unrelated to this skill. This increases the chance of unintended activation, causing the skill to steer user interactions unexpectedly and potentially override more appropriate routing or user intent.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill directs the agent to write a Markdown file by default and names a persistent output path pattern, but it does not require user consent or disclose that content may be stored. This can lead to unexpected file creation, persistence of personal information such as the user's name and goals, and confusion about where sensitive planning data is retained.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: Line L4 hard-codes an English default prompt ('Use $super-individual-90day...') while the surrounding interface metadata is in Chinese. This creates a language-policy concern because the skill appears to impose a specific language without offering user choice or explaining why English is required.

Natural-Language Policy Violations

Low

Confidence: 81% confidence
Finding: All instructions, triggers, and output templates are specified in Chinese, and the skill does not indicate that users may choose another language or that the Chinese-only behavior is a justified regional constraint. This can constitute a language/locale policy issue when a skill effectively forces one language without user opt-in.

Static analysis

No suspicious patterns detected.