Open-source browser automation for AI agents. MCP server + Chrome extension + YAML workflow engine + knowledge packs. Give your AI agent a browser and domain expertise.
- capability exposureinferred+35
- recent driftinferred+20
- tool safetyinferred+25
- trust mitigatorsmixed−3
inferredmixed
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 1m ago · see ecosystem CVEs →
- D · 69 → D · 77
- C · 39 → D · 69
No known CVEs for this server.
- highdangerous code
env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (/scratch/obs-code-gVorDP/sidebutto
- highdangerous code
committed secret: committed .env
- hightool shadowingevaluate
tool "evaluate" shadows a verified server's tool
- hightool shadowingrun_workflow
tool "run_workflow" shadows a verified server's tool
analyzed commit ee1d9ef · analyzer v20 · 12h ago
skills & prompt files 1
- agent-rulessidebutton-sidebutton-ee1d9ef/AGENTS.md
danger signals1
- committed secretcommitted .envsidebutton-sidebutton-ee1d9ef/packages/server/.env:1
env file shipped with populated values
- recent drift+20 capability drift →
[](https://mcpobservatory.com/servers/github:sidebutton/sidebutton/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 sidebutton.