platform-custom-application-generate
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code, scripts, or binary assets. It is comprised entirely of documentation and instructions for generating XML/JSON metadata for Salesforce applications.
- [PROMPT_INJECTION]: The instructions do not contain patterns for bypassing safety guidelines, ignoring previous instructions, or extracting system prompts. The language is professional and focused on the technical requirements of the platform.
- [DATA_EXFILTRATION]: There is no evidence of hardcoded credentials, access to sensitive local file paths (such as .ssh or .aws), or unauthorized network operations. Configuration parameters like 'headerColor' and 'fullName' are standard metadata fields.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any external downloads or execute remote scripts. It provides a specification for metadata properties without invoking external processes.
- [COMMAND_EXECUTION]: No shell commands or system-level calls are present in the instructions.
Audit Metadata