MCP server · trust report

io.github.Agent360dk/browser-mcp

2 checks that ran failed — version behavior and transport config — so this release can’t be trusted as-is.

Publisher
io.github.Agent360dk
Repository
github.com/Agent360dk/browser-mcp
Install
npm:@agent360/browser-mcp, npm:@agent360/browser-mcp, npm:@agent360/browser-mcp, npm:@agent360/browser-mcp
Versions
4
Inspected
5 of 6 checks · 75%
Scored
2026-09-04 · rubric 1.0.0

What we checked

Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.

6 checks2 clean3 flagged1 not inspected
  • Injection surface

    unscannable25% of grade

    Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

    No tool descriptions, server instructions, prompts, or resources were fetched; nothing to scan for injection.

  • Supply chain

    pass25% of grade

    Package provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.

    repository linkage verified

  • Credential hygiene

    pass15% of grade

    How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

    Reads secrets from the environment (e.g. bin/cli.js) — the recommended intake shape. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

  • Permission scope

    warn15% of grade

    Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

    has both shell/exec and network egress — capable of download-and-run, though no such path was observed (index.js: imports child_process and calls exec/spawn; extension/background.js: outbound HTTP/socket call). discloses shell/exec capability: index.js: imports child_process and calls exec/spawn discloses dynamic code execution: extension/background.js: uses new Function(…) Capability DISCLOSURE, not a verdict: static analysis sees the primitive is present and reachable, not whether its use is attacker-controlled.

  • Version behavior

    fail10% of grade

    Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

    vs prior 1.24.0 (minor bump): new capability primitive(s) in source: child_process, dynamic-eval, http-client; new hardcoded outbound host/BCC destination(s): admin.shopify.com, api.slack.com, app.hubspot.com, app.pipedrive.com, browsermcp.dev, calendly.com, console.cloud.google.com, dashboard.stripe.com, github.com, us1.admin.mailchimp.com, www.linkedin.com.

  • Transport config

    fail10% of grade

    Remote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.

    source performs runtime self-update / download-and-execute (bypasses version_behavior); manifest/source references Heartbeat behavior — disclosure

Version history

Each release plotted by grade against the safe line at B. A version that sinks below the line has lost its trusted standing — the shape of a rug-pull.

VersionPublishedGradeScoreInspectedChange
v1.25.0 · current2026-07-24 C72.55/6 · 75%B→C in v1.25.0
v1.24.02026-07-23 B1003/6 · 55%±0
v1.23.02026-07-21 B82.55/6 · 75%±0
v1.16.12026-04-06 B82.54/6 · 65%