analyzing-omnistudio-dependencies
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is authored by a trusted vendor and performs legitimate analysis of Salesforce OmniStudio environments.
- [COMMAND_EXECUTION]: The skill utilizes standard
sf(Salesforce CLI) commands for querying metadata. These commands are scoped to the authenticated target org and are necessary for the skill's primary function of dependency mapping. - [DATA_EXPOSURE]: The skill accesses Salesforce metadata (OmniScripts, FlexCards, Integration Procedures, etc.) for analysis. No patterns of data exfiltration to external or unauthorized domains were detected. It correctly instructs the agent to ask for org aliases rather than hardcoding credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Salesforce record metadata (JSON configurations in PropertySetConfig and DataSourceConfig). While this presents a theoretical attack surface, the skill's operations are limited to parsing these structures for graph construction and reporting purposes.
- [CREDENTIALS_UNSAFE]: The skill does not contain hardcoded secrets. It provides safe templates for API requests and instructs the use of standard Salesforce CLI authentication mechanisms.
Audit Metadata