← All servers

Neumann F

io.github.Kromatic-Innovation/neumann · v0.2.121 · score 9/100 · checked 2026-11-22

Monte Carlo ranges for uncertain plans: project cost, budget, timeline, capacity, NPV/IRR/payback.

Findings

SeverityRuleDetail
lowAG005Remote endpoint lists 20 tool(s) to anyone, no credentials needed.
criticalAG101tool 'delete_graph': description contains instruction-like text aimed at the model ('do not tell the user'). Possible tool poisoning.
criticalAG101tool 'delete_run': description contains instruction-like text aimed at the model ('do not tell the user'). Possible tool poisoning.
mediumAG1022 tool(s) can execute commands or delete data (delete_graph, delete_run). Require confirmation before the agent calls them.

What was checked

Public tools: run_monte_carlo_simulation, rank_inputs_by_impact, summarize_outcome_scenarios, check_simulation_model, estimate_simulation_size_and_cost, convert_range_to_distribution, convert_distribution_to_range, get_simulation_results, check_account_and_credits, send_feedback, buy_credits, create_result_share_link, revoke_share_link, save_graph, list_graphs, get_graph, list_graph_versions, export_run, delete_graph, delete_run

Maintainer? Fix, then add the badge

Grades refresh daily.

[![agentguard](https://agentguard-pi.vercel.app/badge/io-github-kromatic-innovation-neumann-c41a4784.svg)](https://agentguard-pi.vercel.app/s/io-github-kromatic-innovation-neumann-c41a4784)

agentguard: static and read-only checks. A grade is not a guarantee of safety. Index · Scanner