browser-mcp@0.1.64
VERIFIEDPublisher claims: "MCP server + CLI giving AI agents a real, stealth browser (Patchright/Playwright) — per-country identity, self-healing actions, snapshots, multi-step plans, structured extraction, CDP attach." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-30 and scored it 85/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationst+CategoryObserved action
0.1sprocessexited 1: Node.js v22.23.4
0.7sprocessdependency install exit 1
0.8sprocessexec /usr/bin/timeout
0.8sprocessexited 1: Node.js v22.23.4
0.8sclaimedno tools/list reply (exit 1)
0.8sprocessscript backend runs setup only
Static findings
MEDIUM
npx invocation of non-well-known packagedist/engine/launch.js:20 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
Process kill commanddist/engine/launch.js:48 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05