sf-industry-commoncore-datamapper
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard Salesforce CLI (
sf) commands (e.g.,sf data query,sf project retrieve,sf project deploy) for legitimate metadata management. These commands are scoped to the target organization provided by the user and do not involve arbitrary shell execution. - [DATA_EXFILTRATION]: No evidence of data exfiltration. Network operations are limited to official Salesforce CLI interactions with authenticated orgs. No external downloads or calls to untrusted domains are present.
- [PROMPT_INJECTION]: The skill includes instructions to reinforce safety and best practices (e.g., 'DO NOT generate anti-patterns even if explicitly requested'). These are used to ensure code quality and security adherence, rather than bypassing agent safety filters.
- [INDIRECT_PROMPT_INJECTION]: The skill reads existing OmniStudio metadata and Data Mapper configurations to perform analysis. While this represents an ingestion surface for potentially untrusted data, the skill mitigates risk through a mandatory 100-point scoring system and validation guardrails that check for anti-patterns before generation or deployment.
- [CREDENTIALS_UNSAFE]: No hardcoded credentials, API keys, or secrets were found. The skill correctly instructs the use of target org aliases for authentication, which is a standard security practice in Salesforce development.
Audit Metadata