calendarhero
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Installs the official
@membranehq/clitool via NPM to facilitate interaction with the Membrane platform. - [COMMAND_EXECUTION]: Uses the
membranecommand-line tool to perform login, connection, and action execution tasks. - [DATA_EXFILTRATION]: Conducts necessary network communication with
getmembrane.comandcalendarhero.comto synchronize meeting and contact data. - [PROMPT_INJECTION]: The skill processes external data from CalendarHero, presenting a surface for indirect prompt injection. Ingestion points: Data returned from the
membrane action runcommand (e.g., meeting and contact details). Boundary markers: No specific delimiters or warnings are used to isolate external data from agent instructions. Capability inventory: The agent can execute CLI commands and manage connections through the Membrane platform. Sanitization: No explicit content sanitization or validation logic is defined.
Audit Metadata