AI Game - 游戏×AI 资讯
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: ai-game Version: 1.0.4 The skill bundle is a specialized news aggregator for the gaming AI industry. It functions by executing a Python script (scripts/fetch_news.py) that scrapes various RSS feeds and queries a specific news API (aihot.virxact.com). The instructions in SKILL.md are focused on data categorization, professional formatting, and a 'source tracing' protocol to ensure users receive primary source links. There is no evidence of malicious intent, data exfiltration, or harmful prompt injection; the script and instructions are entirely consistent with the stated purpose of providing industry updates.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Using the skill can execute local helper code and make external news/API requests to generate results.
The skill instructs the agent to run a bundled Python script that fetches RSS/API data and writes JSON output. This is expected for a fresh-news skill, but users should know it is not purely static content.
cd ${SKILL_DIR}/scripts && python3 fetch_news.pyUse it when you want fresh game-AI news, and review the bundled script/source list if you need strict control over outbound requests.
If a user includes confidential terms in a search topic, those terms may be sent to the external API provider.
The workflow can send the search keyword to an external AI HOT API. This is purpose-aligned for news search, but it creates an external data boundary.
curl -sH "User-Agent: $UA" "https://aihot.virxact.com/api/public/items?mode=selected&q=<关键词>&take=20"
Avoid using private project names, unreleased plans, or sensitive internal terms as search keywords unless you are comfortable sending them to the listed external service.
Outputs may repeat outdated, mistranslated, or source-contaminated news summaries if the cached data or upstream sources are wrong.
The agent reuses cached retrieved news items for historical summaries. This is expected, but cached or retrieved content can become stale or reflect errors from external sources.
读取 `data/` 目录下对应日期范围的 JSON 文件 2. 合并所有 items,按 URL 去重
Check the included source links for important decisions, and refresh the data when accuracy matters.