athenahealth
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clipackage from the npm registry. This package is maintained by the skill's author and is required to interact with the Membrane platform. - [COMMAND_EXECUTION]: The instructions guide the agent to execute shell commands using the
membraneCLI to authenticate, connect to services, and run actions. These operations are standard for the tool's intended use case. - [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it retrieves and processes external healthcare data from Athenahealth. 1. Ingestion points: Data returned in the
outputfield when running actions such aslist-patientsorget-patientvia themembrane action runcommand. 2. Boundary markers: None explicitly specified in the skill instructions. 3. Capability inventory: Subprocess execution and network access via the Membrane CLI. 4. Sanitization: Not explicitly implemented in the skill code; the skill relies on the agent's default safety filtering and the platform's data handling.
Audit Metadata