design-website
Warn
Audited by Snyk on Mar 27, 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's required workflow (scripts/read_prospect.py as described in SKILL.md Step 1) reads prospect data from arbitrary Google Sheets (user-provided, untrusted) and scripts/generate_website.py then queries the public Unsplash API (and uses returned alt/credit metadata) using values from the sheet to build queries and generate the HTML, so third‑party/user content is ingested and directly influences generation and subsequent API requests.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata