twmd-review-stock
Review the stock: pick 1-2 T1 high-traffic never-reviewed articles, run FACTCHECK Quick Mode + the editorial-room cold read, write a 查證單 under reports/review-stock/ and point the article at it (preReview); promote to curation: verified (verifiedVia: community) only when reader confirmations reach the §1d threshold. Canonical MAINTAINER-PIPELINE §1d. TRIGGER when: user says "審庫存", "review stock", "預審既有文章", or routine `twmd-review-stock` fires.
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 reviews stock articles and checks community reader confirmations via Supabase, which contains user-submitted feedback and interactions.
- 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.