using-b2c-tooling-sdk
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the installation of the
salesforce-b2c-tooling-sdkfrom the official SalesforceCommerceCloud GitHub organization repository. - [REMOTE_CODE_EXECUTION]: The installation process involves executing
pip installagainst a remote Git repository, which is a standard method for distributing early-access developer tools. - [COMMAND_EXECUTION]: The skill uses shell commands for environment setup and installation, and provides Python code snippets for interacting with Salesforce B2C Commerce services.
- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest and process data from external sources that could potentially contain malicious instructions.
- Ingestion points: The agent can retrieve and process external data such as log files (
tail_logs,get_recent_logs), catalogs, and site metadata via the SDK clients (SKILL.md, references/api-catalog.md). - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" markers for the data retrieved from external API calls.
- Capability inventory: The skill grants the agent the ability to perform high-impact operations including deploying cartridges (
find_and_deploy_cartridges), executing jobs (execute_job), and performing file operations via WebDAV (instance.webdav.put) (SKILL.md, references/api-catalog.md). - Sanitization: There is no evidence of explicit sanitization or validation of the content retrieved from B2C Commerce APIs before it is incorporated into the agent's context.
Audit Metadata