global@6.2.0
VERIFIED· install onlyPublisher claims: "W3C Web Model Context Protocol (WebMCP) API polyfill. Let AI agents like Claude, ChatGPT, and Gemini interact with your website via document.modelContext." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-10 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
…e,t){return L_(e,t??($v??=new xv))}let ty=ym(void 0).inputSchema,ny=`__isBrowserMcpServer`;function ry(e){return typeof e==`object`&&!!e&&ny in e&&e[ny]===!0}function iy(e){return`clientOrigin`in e&&(e.clientOrigin===void 0||typeof e.clien…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.No other findings across 922 lines in 7 files.
Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for @mcp-b/global@6.2.0 as of 4d ago. This is the package itself, not its dependencies.