Security audit

V2ex Hot Cn

Security checks for vulnerabilities and agentic risk

Overview

This skill is low-privilege but advertises live V2EX monitoring while its executable returns fixed mock topics, so users could be misled about freshness and provenance.

Review before installing if you need accurate or current V2EX data. This appears low-risk to your system, but it should either implement live fetching or clearly disclose that it is a demo returning mock results.

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 (4)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The manifest description includes very broad trigger phrases such as “V2EX”, “v2”, and “程序员社区”, which are likely to appear in normal conversation outside a clear request to use this skill. This can cause accidental invocation or routing collisions with other skills, increasing the chance of unintended data retrieval or confusing behavior, though the skill itself appears low-risk and informational.

Description-Behavior Mismatch

Medium

Confidence: 97% confidence
Finding: The manifest advertises monitoring of V2EX hot topics, but the script does not perform any monitoring or live retrieval and instead serves fixed sample content. This mismatch undermines trust boundaries: users may rely on the skill for situational awareness or decision-making based on information that is not real or current.

Intent-Code Divergence

Medium

Confidence: 98% confidence
Finding: The function claims to fetch V2EX hot topics but actually returns hardcoded mock data, which is a form of deceptive behavior relative to the documented purpose. In an agent skill, this can mislead users or downstream automation into acting on stale or fabricated information while believing it is live external content.

Natural-Language Policy Violations

Low

Confidence: 96% confidence
Finding: The default rendered output string is in Chinese ("V2EX 今日热门"), and the surrounding docstrings are also bilingual/Chinese-oriented without any option for users to select another language. This is a natural-language locale policy concern because the skill imposes a specific output language by default rather than offering opt-in or documenting a justified regional limitation.

Static analysis

No suspicious patterns detected.