npm-research

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches package data from public npm-related sources (e.g., search/package_info from the npm registry, bundle_size via Bundlephobia, and vulnerabilities checking npm audit advisories) and the workflow requires the agent to read and act on those results to make recommendations, so untrusted README/advisory content could influence behavior.