evernote-webhooks-events
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill architecture ingests external data from Evernote webhooks and the synchronization API without implementing boundary markers or sanitization, creating a potential vulnerability surface.\n
- Ingestion points:
references/implementation-guide.mddefines a webhook router that acceptsuserId,guid,notebookGuid, andreasondirectly from query parameters.\n - Boundary markers: The implementation instructions do not specify the use of delimiters or instructions to ignore commands that may be contained within the synchronized note data.\n
- Capability inventory: The skill uses
Bash(curl:*),Read,Write, andEdittools, which represents the potential impact if the agent follows instructions embedded in note content.\n - Sanitization: The provided code snippets do not include input validation or sanitization routines for the data received from external sources.
Audit Metadata