repair-style
Fix editorial style violations identified in style review changelog while preserving pedagogical content integrity. Trigger on: reparar estilo, fix style, corregir voz, repair tone, resolve style issues, aplicar correcciones.
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 requires reading local style review changelog files matching `project/reports/style-review-*.md` which are authored externally.
- Repository
JaviMontano/mao-scriba
- Revision
4bc8492
- 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.