The Agent Skills Directory

[SAFE]: The skill implements robust input validation in scripts/verify-and-assign.sh. Specifically, the user-supplied count is validated as a small integer, and each permission set name is checked against a strict regular expression (^[A-Za-z][A-Za-z0-9_]{0,79}$) before being used in SOQL queries or shell commands, effectively mitigating common injection vectors.
[SAFE]: A production safety guard is included in the script. It queries the target organization's metadata to ensure it is a sandbox, trial, or developer edition before proceeding with any data modifications, preventing accidental privilege changes in production environments.
[SAFE]: The skill uses official tools (sf CLI and jq) for all interactions with the Salesforce API. All network operations are directed at the authenticated Salesforce instance, and no sensitive credentials or data are exfiltrated to external domains.
[SAFE]: Temporary files used to capture API error messages are handled securely using mktemp and are cleaned up immediately after use, preventing local data leakage or persistence.

service-omni-supervisor-permset-assign