evernote-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documentation and implementation guide provide standard patterns for interacting with the Evernote API using the official SDK.
  • [PROMPT_INJECTION]: Risk Factor (Indirect): The skill ingests data from external note titles and content, creating a potential surface for indirect prompt injection if the retrieved data is not treated as untrusted. \n
  • Ingestion points: references/implementation-guide.md (SearchService methods). \n
  • Boundary markers: None. \n
  • Capability inventory: The skill permits Bash, Write, and Edit operations via the platform configuration. \n
  • Sanitization: No content-level sanitization is performed on retrieved note data before it is presented to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 04:43 PM