High-risk tools in Rokha
15 of the 216 tools in Rokha 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
-
auth_wallet_verifyExecuteStep 2: submit the signed challenge. On success returns session_token — a JWT to send as `Authorization: Bearer <token>` on every subsequent MCP/API request, unlocking the owner...
-
harness_authorExecuteConfigure a Harness — a skill (or instruction) wired to run — and get back its config. A harness wraps ONE unit of work via `kind`: 'skill' (a registry skill, configured to run)...
-
orbitx__orbitx_gc_focusExecuteEnter sticky group-chat mode. When the user says I want to chat in the group chat — call this. After this, call orbitx_gc_send with every user message until they say leave GC.
-
registry_adoptExecuteThe select → input → run door: materialize YOUR OWN runnable copy of any published rig listing (find provider_id + external_id via registry_search; the listing must carry a meta...
-
registry_list_serverExecutePut a remote MCP server in front of every agent that searches Rokha — FREE, permanently, on any account including the free tier. No seat, no card, no paywall. Pass the streamabl...
-
rig_authorExecuteBuild + save a multi-node Rig as a GRAPH the runtime executes for real — the agent-side mirror of the human Rig Builder canvas. `structure_type`: 'dag' (acyclic; parallel + real...
-
rig_runExecuteRUN a rig, for real, right now. Without this an outside agent could AUTHOR a rig, schedule it and hang a webhook on it — but never run one on demand, and so nev...
-
sandbox_execExecuteRun a REAL command in the user's active session sandbox (isolated cloud shell + live MCP). kind='bash' (`command`) | 'mcp' (`endpoint`, `action` list|call, `tool`, `arguments`) ...
-
sandbox_startExecuteStart the user's session sandbox (isolated cloud shell — the safe place to test untrusted tools; sandbox_exec runs work inside it). SPENDS the daily run allowance: 1 run, or 3 w...
-
sandbox_stopExecuteStop the user's session sandbox gracefully (state → 'ending'; queued work drains). Frees nothing to re-spend — the day's allowance was spent at start — but a stopped sandbox is ...
-
send_agent_messageExecuteSend a message to a Rokha agent (default 'rokha-agent') and get its reply. With a logged-in identity (Authorization: Bearer <JWT>) the agent acts AS you — it can run your rigs (...
-
signet_approveExecuteApprove one of YOUR pending action requests (the ones a mandate with require_approval:true escalates). The mandate is RE-AUTHORIZED at approval time — if it expired or was revok...
-
singularityagent__meshExecuteInvestigate one subject against a stated objective by calling several of these tools in a searched order, and come back with the facts, the path that proved them, and an explici...
-
studio_doorsExecuteWHAT ROKHA COSTS — the plans and the license. Rokha is the AI studio and launchpad: build in the Studio, launch on the Rokha Network, and the Network carries it. NETWORK (monthl...
-
x_link_startExecuteStart a headless X link. Returns a one-time nonce; POST that exact string from the X account you are claiming (the post may say anything else too), then call x_link_verify with ...
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.