Is efferent@1.0.0 safe to install?

efferent@1.0.0

VERIFIED

Publisher claims: "A local MCP server that lets Claude (or any MCP client) drive the user's own browser — with their existing sign-ins — in a separate window of its own, so pages can be opened, read, and acted on without stealing focus or interrupting the user's work." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher brandonmlicea · joined 0 days agoInstalls 0Last detonated 2 h ago

$npx skills add efferent

Watch Report an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-06 and scored it 83/100 (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 · 0 s · 2 scenarios · 0 deviations

t+CategoryObserved action

0.0sprocessno install scripts in bundle

0.2sprocessexec /usr/bin/date

0.2sprocessexec /usr/bin/timeout

0.2sclaimed8 tools: browsers, tabs, open, read, act, screenshot, eval, close

0.2sprocessscript backend runs setup only

0.2sprocessno install scripts to re-run

Static findings

LOW

Prompt injectionREADME.md:35 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.

AST01

MEDIUM

URL using raw IP addresseval/run.mjs:27 · URL using raw IP address — may bypass domain-based filteringFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.

AST07

HIGH

Outbound HTTP to raw IP addresseval/run.mjs:27 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.

AST07

LOW

Authorization escalation languageREADME.md:35 · Authorization escalation language · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.

AST01

Cost to the agent

Instructions loaded

≈35 tok

1 file · 31 in bundle

Tool list per prompt

≈1,091 tok

8 tools · 136 per tool

Handshake

164 ms

launch to tools/list, stdio

Undocumented tools

description under 20 chars · avg 202

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.