High-risk tools in MedSci Agent
5 of the 28 tools in MedSci Agent 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
-
differential_expressionExecuteRun differential expression analysis between cell groups. Identifies genes that are significantly up- or down-regulated between clusters or conditions.
-
sandbox_run_jobExecuteExecute a command in an existing Docker sandbox and capture stdout, stderr, exit code, duration, and artifact metadata. Synchronous execution only.
-
cluster_cellsExecuteCluster cells in a preprocessed single-cell dataset using Leiden or Louvain community detection. Returns cluster assignments and UMAP coordinates.
-
preprocess_omicsExecutePreprocess a single-cell RNA-seq dataset: filter cells/genes, normalize, log-transform, and identify highly variable genes. Returns QC summary.
-
sandbox_prepareExecuteCreate or verify an isolated Docker sandbox for the workspace. Optionally apply a container template and network policy. Idempotent — returns existing sandbox info if already cr...
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.