service-omni-command-center-configure
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
sf(Salesforce CLI),jq, andpython3to manage Salesforce metadata. These operations are standard for Salesforce development workflows and target the user's authenticated orgs. - [INDIRECT_PROMPT_INJECTION]: The skill retrieves and modifies XML settings from a Salesforce org. It mitigates injection risks by using structured XML parsing via Python's
ElementTreeand validating user inputs against a hardcoded whitelist of supported settings. - [DYNAMIC_EXECUTION]: The unit tests utilize
subprocess.runto execute local shell scripts during the test phase. This is a standard testing pattern used to verify script behavior in a controlled environment and does not impact the safety of the skill's core functionality.
Audit Metadata