salesforce

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the official NPM registry. This is a tool provided by the vendor to facilitate the skill's functionality.
  • [COMMAND_EXECUTION]: The skill utilizes the membrane command-line interface to perform several operations, including authentication, connection management, and executing Salesforce-specific actions or proxy requests.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external source (Salesforce) which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: Data is retrieved from Salesforce via actions like get-record, execute-soql-query, and direct API proxy requests (SKILL.md).
  • Boundary markers: There are no explicit instructions to use boundary markers or to ignore potential instructions embedded within the retrieved Salesforce data.
  • Capability inventory: The skill allows for significant operations including creating, updating, and deleting Salesforce records, as well as executing arbitrary SOQL/SOSL queries.
  • Sanitization: No explicit sanitization or validation of the data retrieved from Salesforce is mentioned before the data is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:01 PM
Security Audit — agent-trust-hub — salesforce