High-risk tools in Agent Store
4 of the 19 tools in Agent Store 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
-
fleet_dispatchExecuteDispatch a task to the Asteroid Fleet. Routes through pipeline: classification → worker → QA gates → response.
-
gbrain_queryExecutegbrain_query
-
gbrain_thinkExecuteRun multi-hop synthesis across wiki pages. Produces a cited answer
-
reindex_wikiExecuteRebuild the FTS5 search index from scratch.
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.