twmd-probe
Run external hot-spot probe (探測器 / 新聞雷達). Weekly via twmd-news-lens-weekly or observer-triggered. TRIGGER when: user says "跑探測器", "掃熱點", "probe", "外部缺口", "新聞雷達", "建議可以寫什麼主題".
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The workflow utilizes WebSearch and WebFetch to read external web pages and news articles, representing outsider-authored content accessed via active search.
- Repository
frank890417/taiwan-md
- Revision
3f3766c
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.