platform-sharing-rules-generate
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized exfiltration were detected.
- [COMMAND_EXECUTION]: The skill utilizes the Salesforce CLI (sf) and standard shell commands (grep) to manage metadata. These tools are standard for the platform and their use is restricted to the local project environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes existing XML metadata files from the local project. Although this represents an ingestion of external data, the risk is mitigated by a mandatory Phase 4 confirmation workflow that requires the user to explicitly approve any proposed changes before they are applied to the filesystem.
Audit Metadata