evernote-core-workflow-a
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface where external content is ingested to create or modify Evernote notes.
- Ingestion points: The
createNote,createHtmlNote, andappendToNotemethods inreferences/implementation-guide.mdaccept content from the agent's context to be sent to the Evernote API. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are included in the generated note content.
- Capability inventory: The skill uses the Evernote
noteStoreAPI to create and update notes in a user's account. - Sanitization: The implementation includes a
htmlToENMLhelper that sanitizes input by removing<script>,<form>, and<iframe/>elements, as well as HTML event handlers, which follows best practices for Evernote content management. - [SAFE]: The skill uses standard OAuth-based authentication patterns for Evernote and does not contain hardcoded credentials, suspicious network operations, or obfuscated code.
Audit Metadata