b2c-scapi-schemas
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes OpenAPI schema definitions retrieved from external SCAPI endpoints. These schemas constitute untrusted data that could theoretically contain malicious instructions designed to influence the agent's behavior during inspection.
- Ingestion points: SCAPI OpenAPI schemas retrieved via the
scapi_schemas_listtool or theb2cCLI. - Boundary markers: No specific boundary markers or instructions to ignore instructions within the fetched schemas are defined.
- Capability inventory: The skill has access to CLI execution (
b2c), network requests (scapi_execute,scapi.request), and file system operations (saving schemas to files). - Sanitization: No content validation or sanitization of the schema data is specified before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill recommends using
npx @salesforce/b2c-clifor users who do not have the tool installed globally. This fetches and executes the official command-line interface from Salesforce's public registry, which is a standard and expected operation for interacting with the Salesforce Commerce Cloud platform.
Audit Metadata