mf

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

• Third-party content exposure detected (high risk: 0.85). In reference/module-info.md (Step 2a consumer mode), the skill runs node scripts/module-info.js --context '<MFContext-JSON>' --module '<module-name>', and scripts/module-info.js fetches mf-manifest.json from a remote publicPath/remoteEntry URL at runtime and ingests the fetched JSON fields (exposes, remotes, shared) into the LLM context.