drchrono

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform operations such as listing patients and creating appointments via the DrChrono API.
  • [EXTERNAL_DOWNLOADS]: Instructs the user to install the @membranehq/cli package, which is the official tool provided by the vendor.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing external healthcare data. Ingestion points: Retrieves patient records, clinical notes, and messages from DrChrono. Boundary markers: None present to isolate external data from agent instructions. Capability inventory: Ability to run actions and requests through the membrane CLI. Sanitization: No explicit validation or sanitization of ingested patient data is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 03:04 PM