platform-apex-generate
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow requires the execution of the
sfCLI andrun_code_analyzer(Salesforce Code Analyzer) to validate and test all generated Apex code. These tools are standard for the platform and are used here to ensure code quality and security by identifying and fixing violations before deployment. - [PROMPT_INJECTION]: The skill processes existing Apex source files to inform its generation process, creating an indirect prompt injection surface where malicious code in existing files could attempt to influence the agent's behavior. 1. Ingestion points: Phase 1, Step 3 involves reading existing .cls and .trigger files. 2. Boundary markers: No explicit delimiters are specified for the imported code context. 3. Capability inventory: The skill can create new files and execute commands via the sf CLI. 4. Sanitization: This risk is mitigated by the mandatory Step 6, which uses run_code_analyzer to perform a security scan on all generated content.
Audit Metadata