cali-degustia-client-news-watch
Warn
Audited by Snyk on Jul 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM context via Step 1 when the skill reads and extracts visible text from user-provided
.html/.mdclient report files (which are not authored by the operating user), turning that HTML/Markdown body text into prompt-visible prose for later steps.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata