trmnl-plugin-builder

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly describes TRMNL polling arbitrary polling_url endpoints and POSTing to author-controlled plugin_markup_url (see references/private-plugins.md and references/advanced-third-party.md, plus assets/settings.yml's polling_url) so runtime content from external, untrusted servers/URLs will be ingested and can determine markup and plugin behavior, enabling indirect prompt-injection.