Security audit

对标筛选

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only benchmark-evaluation skill whose Chinese-language default and broad routing are usability notes, not security-risk behavior.

Install this if you want a Chinese-first workflow for deciding which creators or one-person businesses are worth studying. Users who prefer another language should explicitly ask for it, and maintainers may want to tighten the activation wording to avoid use on unrelated general research tasks.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (8)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The description says to use the skill whenever Codex needs to judge whether a person, creator, or business is worth studying, with several broad decision goals. This is expansive and lacks explicit trigger boundaries or negative examples, increasing the chance of unintended invocation for general advice or research requests.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: "Use this skill when the user needs help choosing who to study, who to copy from, or whether an existing benchmark is actually useful" overlaps with common advisory or research tasks. Because it does not clearly distinguish this skill from adjacent skills or state when not to activate it, the trigger remains vague.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The default contract states "write in Chinese" unless the user says otherwise. This imposes a language preference by default rather than offering a neutral choice or explicit opt-in, which is a natural-language policy concern.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The default prompt uses broad routing language ('Use $benchmark-filter to evaluate this creator...') without explicit trigger boundaries or user-intent checks. In an agentic system, this can cause over-activation or inappropriate invocation on loosely related inputs, increasing the chance of unwanted data processing, misrouting, or prompt-injection exposure through unnecessary skill use.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: The prompt mandates Chinese output ('in Chinese') without indicating that this depends on user preference or locale. This can override user expectations, reduce usability, and in some contexts cause information to be presented in a language the user cannot verify, which is a policy and trust issue rather than a direct code-execution risk.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: This file contains user-facing natural-language instructions exclusively in Chinese and does not indicate that the skill is region-specific or that users may opt into another language. That can violate a language/locale policy requiring neutrality or user choice.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The entire skill reference is written in Chinese with no indication that users may choose another language or that the language restriction is required for a region-specific purpose. Under the policy rules, forcing a specific language without opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 93% confidence
Finding: This markdown template appears to require Chinese as the interaction language, and there is no indication that users may choose another language or that the template is intentionally limited to a Chinese-speaking context. Under the policy rule for natural-language constraints, forcing a specific language without opt-in can be a policy violation.

Static analysis

No suspicious patterns detected.