salesforce
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage from the npm registry. This is a well-known service and the package is the official tool provided by the skill's author. - [COMMAND_EXECUTION]: The skill uses the
membranecommand-line interface to interact with Salesforce APIs. This includes searching for connectors, managing connections, and executing actions. These commands are necessary for the skill's primary functionality. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it retrieves and processes data from Salesforce records (such as Leads, Contacts, and Cases) which may contain untrusted content.
- Ingestion points: Salesforce record data retrieved via the
membrane action runandmembrane requestcommands documented inSKILL.md. - Boundary markers: None identified in the provided documentation.
- Capability inventory: The skill performs subprocess calls to the
membraneCLI to perform CRUD operations on Salesforce data. - Sanitization: No explicit sanitization or validation of the retrieved Salesforce data is mentioned in the skill instructions.
Audit Metadata