vivabox-group-skills/module-federation-load-component
Componente de carga para Module Federation
100
100%
Does it follow best practices?
Impact
—
Average score across 4 eval scenarios
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required runtime path is the host’s `LoadComponent` usage, which loads remote MFEs from `lazyElement.url` (public/outsider-authored code/content served by other parties) and injects it into the agent/LLM context via the remote’s loaded module text/exports.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill relies on Module Federation runtime loading remote bundles (remoteEntry.js) from the configured remote.url at runtime — i.e., fetching and executing remote JavaScript from remote.url/remoteEntry.js — which causes external code to execute in the host.
- Audited
- Security analysis