evernote-performance-tuning

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from an external source (Evernote) which could contain hidden instructions (Indirect Prompt Injection).
  • Ingestion points: Data is retrieved via findNotesMetadata, getNote, and search results from the Evernote API (references/implementation-guide.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided implementation examples.
  • Capability inventory: The skill allows the agent to use Read, Write, Edit, and Grep tools, which could be abused if malicious instructions are successfully injected via a note (SKILL.md).
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from Evernote before it is processed by the agent or presented in the context.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 04:46 PM