ghost-blog
Warn
Audited by Snyk on May 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests untrusted, user-generated public content — e.g., g.get("admin/posts/...", formats="html") in ghost_md.py/SKILL.md (reading blog post HTML), the YouTube oEmbed fetch in SKILL.md, and Unsplash calls via ghost_api._unsplash_get — and then interprets and uses that data to build/update posts (Lexical embeds, feature images, captions), so external content can materially influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata