axf@2.1.4

VERIFIED· startup only

Publisher claims: "Agent eXoskeleton Framework control plane for workspace-native agent capabilities over MCP." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher smartergpt · publishing for 325 daysInstalls 0Last detonated 40 min ago
$claude mcp add axf -- npx -y @smartergpt/axf
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the code
What we saw when it ran
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it under the guard. Startup only; authenticated tool behavior not tested. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- npx -y @smartergpt/axf

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-21 and scored it 85/100 (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 · 20 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
20sclaimedstartup only: exited (0) before answering · axf promote global.acme.status --to active axf scout --check axf integrate codex --check axf mcp
20sprocessscript backend runs setup only
20sprocesssecond launch, clock +45 days, CI unset

Static findings

LOW
Fake system instruction headerdocs/01-vocabulary.md:177 · Fake system instruction header — mimics internal system structure · informational: not an instruction file## Internal ruleFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Destructive file system command detectedsrc/core/family-loader.js:280 · Destructive file system command detected// Build a minimal argsSchema from an args descriptor. The family formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/core/codex-integration.js:187 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: { ...env, ...server.rootEnvironment },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsadapters/cli/index.js:18 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: ctx.runtime?.env ?? process.env,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandsrc/core/codex-integration.js:1 · File permission modification command — agent changes file ownership/permissionsimport { readFile, writeFile, rename, stat, chmod } from "node:fs/promises";Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Authorization escalation languageREADME.md:53 · Authorization escalation language · informational: not an instruction filepublished terms. Outside a fitted workspace, with no root override, this exampleFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈55 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

No advisories in OSV for @smartergpt/axf@2.1.4 as of 14 min ago. This is the package itself, not its dependencies.