High-risk tools in ChiefLab
8 of the 45 tools in ChiefLab are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
chieflab_continue_launch_loopExecute[chieflab_* alias of chiefmo_continue_launch_loop] Resume a ChiefLab launch loop from runId. USE WHEN an agent has already called chieflab_get_users_after_build / chiefmo_launch...
-
chieflab_execute_approved_actionExecuteP71 — closed-loop executor wrapper. USE WHEN chiefmo_approve_action just succeeded on an action whose executionMatrix.mode is oauth_connector or api_key_connector AND connectorR...
-
chieflab_helpExecuteFIRST TOOL — call before anything else when you don't know what ChiefLab does or where to start. Returns the operator menu + workspace state (connectors wired, last run, signup ...
-
chieflab_launch_productExecuteOperator: chieflab-launch (primary). Spec v0.1 reference implementation of the orchestrator. End-to-end launch loop: repo-grounded positioning + per-channel drafts (linkedin, x,...
-
chieflab_persistence_healthExecuteP91 — verify the persistent stores. Probes proof_ledger / publishing_targets / company_profiles tables (Supabase) OR confirms the in-memory fallback. USE WHEN the user just ran ...
-
chieflab_regenerate_visual_assetExecuteP72 — regenerate a single visual asset (LinkedIn graphic, X graphic, landing hero, etc.) with a different style / fidelity / headline / model. USE WHEN a reviewer hits 'Regenera...
-
chieflab_review_visual_assetExecuteP104 — approve or reject a single visual asset (LinkedIn graphic / X image / landing hero / Product Hunt gallery / carousel slide). USE WHEN a reviewer hits 'Approve' or 'Reject...
-
chieflab_signup_workspaceExecuteUSE WHEN the user has no ChiefLab API key yet and you've gotten a 401 / 'authentication required' error from any other tool. Agent-first signup: creates a new workspace and retu...
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.