omnistudio-omniscript-generate

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill does not contain any malicious patterns such as prompt injection, data exfiltration, or unauthorized command execution.
  • [COMMAND_EXECUTION]: The skill uses the Salesforce CLI (sf) to interact with authenticated environments. This usage is consistent with its stated purpose of managing Salesforce metadata.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied business requirements to generate structured JSON metadata. While this represents an ingestion surface for untrusted data, the provided scripts (check-duplicate-omniscript.sh, deploy-omniscript.sh) implement regex-based validation on shell variables to prevent SOQL injection and shell command manipulation.
  • [SAFE]: The documentation in references/best-practices.md provides explicit security guidance, advising users to process sensitive data server-side and avoid client-side exposure in the OmniScript JSON structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 08:27 AM