service-omni-command-center-analyze
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the Salesforce CLI (
sf) andjqto perform data analysis. All shell variable interpolations (such as org aliases and query strings) are properly double-quoted to prevent command injection, and the tool usage is limited to read-only data queries. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Salesforce queries. It employs strict regular expression validation on user-supplied identifiers—specifically checking for Salesforce User ID patterns or email-formatted usernames—to prevent SOQL injection and ensure that only valid identifiers are used in query construction.
- [DYNAMIC_EXECUTION]: The test harness in the
scripts/tests/directory utilizes Python'ssubprocess.runto execute the skill's bash scripts for contract validation. This is a standard practice for development and testing and does not involve the execution of untrusted external code or dynamic input during normal skill operation.
Audit Metadata