mcp-server-ssh@1.0.5
CAUTIONPublisher claims: "MCP server for SSH remote access: execute commands, transfer files via SFTP, generate SSH key pairs" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Server started and answered tools/list.- Tested
- MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
- Not tested
- what the tools do when called with real credentials
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 the honeypot saw
- no credential files read · no network
- What we could not test
- what the tools do when called with real credentials
Reasonable to connect. No credential asked for, no third-party host named, Server started and answered tools/list.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 1.0.3
vet-skills diff mcp-server-ssh 1.0.3 1.0.5This version reaches for something 1.0.3 did not: 3 new credential files (~/.ssh/id_ecdsa, ~/.ssh/id_ed25519, ~/.ssh/id_rsa). Compared from the two recorded runs, not from source.
- New credential files
- ~/.ssh/id_ecdsa, ~/.ssh/id_ed25519, ~/.ssh/id_rsa
1.0.3 was not run in the sandbox (static only); the comparison covers what static analysis recorded only. Only one of the two runs produced a tool list; tools are not compared.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-15 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 26 s · 2 scenarios · 0 deviationsStatic findings
"3. **Auto-detect** — if neither key nor password given, tries ~/.ssh/id_ed25519, ~/.ssh/id_rsa, ~/.ssh/id_ecdsa.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose..describe("Path to private key file (default: auto-detects ~/.ssh/id_ed25519 etc.)"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."If no auth is provided, auto-detects ~/.ssh/id_ed25519, id_rsa, or id_ecdsa.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."3. **Auto-detect** — if neither key nor password given, tries ~/.ssh/id_ed25519, ~/.ssh/id_rsa, ~/.ssh/id_ecdsa.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary>Claude Code for VS Code Extension</summary> > This section is for the **Claude Code VS Code extension**, not GitHub Copilot. If you use VS Code with GiFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."If no auth is provided, auto-detects ~/.ssh/id_ed25519, id_rsa, or id_ecdsa.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."No default SSH key found at ~/.ssh/id_ed25519, ~/.ssh/id_rsa, or ~/.ssh/id_ecdsa."));Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose..describe("Path to private key file (default: auto-detects ~/.ssh/id_ed25519 etc.)"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary>Codex</summary> Use the Codex CLI: ```bash codex mcp add ssh -- npx -y mcp-server-ssh ``` Or edit `~/.codex/config.toml`: ```toml [mcp_servers.ssh] comFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."No default SSH key found at ~/.ssh/id_ed25519, ~/.ssh/id_rsa, or ~/.ssh/id_ecdsa."));Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// A stray error from a forwarded socket or a channel must not kill theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
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
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim bacarrdy: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.