Skills/Glama/remote-ssh-server

remote-ssh-server@0.1.3

VERIFIED· install only

Publisher claims: "Enables MCP clients to store encrypted SSH host credentials and execute remote commands over pooled SSH connections, including single commands, prompt-answering interactive runs, and multi-step playbooks. Hosts can be listed, created, updated, and deleted through tools, with credentials kept server-side and never echoed back." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher xlbbb-cn · publishing for 260 daysInstalls 0Last detonated 3d ago
$npx skills add remote-ssh-server
WatchReport an issue

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

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
SECRET_KEYWORDSConfiguration, not credentials: MASTER_KEY_BYTES, MCP_SSH_CONFIG_DIR, MCP_SSH_MASTER_KEY, MCP_SSH_POOL_IDLE_MS, MCP_SSH_POOL_MAX_HOSTS, TOPIC_KEYS
Where it talks to
no vendor host named in the codeAlso githubusercontent.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names githubusercontent.com as well as its own vendor. The guard injects SECRET_KEYWORDS only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- <the server's command>

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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-15 and scored it 81/100 (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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
Privileged sudo commandtest/features_smoke.mjs:278 · Privileged sudo command — agent may execute with elevated privilegessudo apt updateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo commandtest/smoke.mjs:170 · Privileged sudo command — agent may execute with elevated privilegesif (legacy[0].command !== "sudo apt update") {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/build-mcpb.mjs:90 · npx invocation of non-well-known package — may execute untrusted codeexecSync(`npx --yes @anthropic-ai/mcpb pack "${stage}" "${out}"`, {Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Unicode escape sequence detectedsrc/tools/help.ts:32 · Unicode escape sequence detected — may contain obfuscated payloads…\u4ea4\u4e92\u5f0f TUI", "", "\u76f4\u63a5\u8fd0\u884c `remote-ssh-cli` \u8fdb\u5165\u4ea4\u4e92\u83dc\u5355\uff0c\u652f\u6301\uff1a\u5217\u51fa\u3001\u67e5\u770b\u3001\u521b\u5efa\u3001\u66f4\u65b0\u3001\u5220\u9664\u4e3b\u673a\u3002", ""…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Privileged sudo command.github/workflows/publish.yml:215 · Privileged sudo command — agent may execute with elevated privilegessudo install -m 755 mcp-publisher /usr/local/bin/mcp-publisherFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Unicode escape sequence detectedsrc/tools/help.ts:36 · Unicode escape sequence detected — may contain obfuscated payloads"### \u5217\u51fa\u6240\u6709\u4e3b\u673a",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Privileged sudo commandtest/smoke.mjs:185 · Privileged sudo command — agent may execute with elevated privileges# @on "sudo apt install -y nginx"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Unicode escape sequence detectedsrc/tools/help.ts:28 · Unicode escape sequence detected — may contain obfuscated payloads"\u5b89\u88c5\u540e\u53ef\u76f4\u63a5\u4f7f\u7528 `remote-ssh-cli` \u547d\u4ee4\u3002",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagescripts/build-mcpb.mjs:84 · npx invocation of non-well-known package — may execute untrusted codeexecSync(`npx --yes @anthropic-ai/mcpb validate "${join(stage, "manifest.json")}"`, {Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandsrc/master_key.ts:51 · File permission modification command — agent changes file ownership/permissions// Best-effort chmod for the case where writeFile didn't honour mode.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Privileged sudo commandtest/smoke.mjs:162 · Privileged sudo command — agent may execute with elevated privilegessudo apt updateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Unicode escape sequence detectedsrc/tools/help.ts:21 · Unicode escape sequence detected — may contain obfuscated payloads"# \u6216\u8005\u4ece\u6e90\u7801\u6784\u5efa\u5e76\u5b89\u88c5",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Privileged sudo commandsrc/ssh.ts:137 · Privileged sudo command — agent may execute with elevated privileges// xterm-sized PTY. sudo and similar tools require a PTYFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo commandtest/features_smoke.mjs:263 · Privileged sudo command — agent may execute with elevated privilegessudo apt updateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo commandtest/smoke.mjs:192 · Privileged sudo command — agent may execute with elevated privilegesif (structured[0].command !== "sudo apt install -y nginx") {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Unicode escape sequence detectedsrc/tools/help.ts:18 · Unicode escape sequence detected — may contain obfuscated payloads"# \u4ece GitHub Packages \u5b89\u88c5\uff08\u5df2\u53d1\u5e03\u7684\u7248\u672c\uff09",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07

Cost to the agent

Instructions loaded
≈1,842 tok
2 files · 35 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

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

remote-ssh-server@0.1.3 safety verdict: Verified (install only) — KillerSkills