service-omni-presence-user-config-deploy
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the Salesforce CLI (
sf) andjqto manage metadata deployments and process JSON data. These operations are scoped to the intended functionality of managing Salesforce configurations. - [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided input such as agent usernames and configuration names. It mitigates injection risks by applying a custom
xml_escapefunction to sanitize data before interpolation into XML metadata templates and using strict regular expression validation for developer names. - [SAFE]: A 'safe_to_write' guard is implemented in
scripts/deploy-and-report.sh. This logic queries the target Salesforce organization and blocks deployment if the environment is identified as a production instance, effectively preventing accidental modifications to live customer data.
Audit Metadata