hubspot
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clinpm package. This is a vendor-owned utility from the author 'membranedev' (Membrane) that is necessary for the skill's functionality. - [COMMAND_EXECUTION]: The skill uses various
membraneCLI commands to perform operations like connecting to HubSpot, searching for actions, and executing CRM requests. These are standard and authorized uses of the vendor's tool. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its ability to read and process data from HubSpot CRM records. Ingestion points: Data retrieved via contacts, deals, and notes actions. Boundary markers: Not explicitly defined in the instructions. Capability inventory: Network requests via
membrane requestand CRM write operations. Sanitization: Handled by the Membrane platform's action schemas.
Audit Metadata