An auditable workbench for agent-assisted computational research—turning evidence, experiments, analyses, and decisions into reviewable, replayable state.
- capability exposure inferred + 22
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 8m ago · see ecosystem CVEs →
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit a92f054 · analyzer v28 · 5h ago
skills & prompt files 8
- agent-rules Endofthestars-benchwork-a92f054/AGENTS.md
- skill Endofthestars-benchwork-a92f054/plugins/benchwork/skills/benchwork-design/SKILL.md
- skill Endofthestars-benchwork-a92f054/plugins/benchwork/skills/benchwork-evaluate/SKILL.md
- skill Endofthestars-benchwork-a92f054/plugins/benchwork/skills/benchwork-implement/SKILL.md
- skill Endofthestars-benchwork-a92f054/plugins/benchwork/skills/benchwork-investigate/SKILL.md
- skill Endofthestars-benchwork-a92f054/plugins/benchwork/skills/benchwork-orchestrate/SKILL.md
- skill Endofthestars-benchwork-a92f054/plugins/benchwork/skills/benchwork-pilot/SKILL.md
- skill Endofthestars-benchwork-a92f054/plugins/benchwork/skills/benchwork-resume/SKILL.md
[](https://mcpobservatory.com/servers/github:Endofthestars/benchwork/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of Endofthestars.