slide-builder
Warn
Audited by Snyk on Apr 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's required workflow (Step 7 "Test") instructs the agent to open the deployed URL with browser-automation and take screenshots, while the skill docs and templates allow/encourage embedding and loading arbitrary external content (iframes via core-frontmatter, remote images/remote-assets, Tweet/Youtube components in core-components, and theme/package installs via scripts/init.sh which runs pnpm install), so the agent will load and render untrusted public third‑party content as part of its runtime flow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata