desktop-commander
Not malicious, needs a look Reviewed: expected behaviour
Bawwab's static rules found patterns that deserve a human look. This is not a finding that the package is malicious; the review notes below say what each pattern turned out to be.
Why it was flagged
The static rules marked this “Not malicious, needs a look” because of:
credential-access: Touches credentials or secrets (high, 2× · first at dist/server.js:553)injection.covert-action: Tells the AI to read or send sensitive data (high, 1× · first at skills/terminal/SKILL.md:198)
- Kind
- Plugin
- Source
- github
- Repository
- wonderwhy-er/DesktopCommanderMCP / plugins/claude
- Commit
75048278f4866f0d8bde26f6f9aa3b8d39dca870- Listed in
- anthropics/claude-plugins-official
- Popularity
- 10,374 GitHub stars (2026-11-20) (official, always included)
- Link
- https://github.com/wonderwhy-er/DesktopCommanderMCP/tree/75048278f4866f0d8bde26f6f9aa3b8d39dca870/plugins/claude
- Scanned
- 2026-11-20T23:15:15+00:00
- Scan time
- 16.8 s
- Scanned as
- plugin
Review note: The bundled Desktop Commander server's install script sends an anonymous install telemetry event; the rest is prompt text, a file-type list and an env copy for a launched Chrome.
Findings (5)
injection.covert-action: Tells the AI to read or send sensitive data high
skills/terminal/SKILL.md:198
OWASP LLM LLM01 Prompt InjectionOWASP LLM LLM02 Sensitive Information DisclosureOWASP Agentic ASI01 Agent Goal HijackOWASP Agentic ASI02 Tool Misuse and ExploitationMITRE ATLAS AML.T0051.001 LLM Prompt Injection: IndirectMITRE ATLAS AML.T0110.000 AI Agent Tool Poisoning: Definition and InstructionsMITRE ATLAS AML.T0086 Exfiltration via AI Agent Tool InvocationCWE CWE-1427 Improper Neutralization of Input Used for LLM Prompting
before running; run read-only inspection first
What this means: Instructions to read keys or secrets, include them in replies or send them somewhere, or to do a hidden step first, are how injected text steals data.
The rule's general advice: Do not install unless you can explain why this text needs those files. (see the review note for this case)
Known false alarm
Etiquette advice in the terminal skill: preview risky commands before running them and do read-only inspection first. It is a caution, not a hidden action.
Reviewed by Claude (AI-assisted review), 2026-11-21
install-script: Runs code at install time med
package.json:29
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesOWASP Agentic ASI05 Unexpected Code Execution (RCE)MITRE ATLAS AML.T0010.001 Supply Chain Compromise: SoftwareMITRE ATLAS AML.T0011.001 User Execution: Malicious Package
[server desktop-commander] node dist/track-installation.js && node dist/npm-scripts/verify-ripgrep.js || node -e "process.exit(0)"
What this means: Install hooks run automatically with your privileges before you can review anything.
The rule's general advice: Read the script; prefer packages with no install hooks. (see the review note for this case)
Expected for what this tool does
The Desktop Commander npm postinstall runs dist/track-installation.js, which POSTs an anonymous 'package_installed' event (platform, Node version, install method from the command line, a random client ID) to the project's telemetry endpoint, then checks ripgrep. The script documents itself; failures are ignored.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
dist/server.js:553
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
[server desktop-commander] - Looking for configuration/setup files: ".env", "dockerfile", "tsconfig.json"
What this means: Reads files or environment holding keys, tokens or sessions.
The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)
Known false alarm
Tool-description text suggesting the assistant search for files such as .env or tsconfig.json when looking for config files. It does not read any file.
Reviewed by Claude (AI-assisted review), 2026-11-21
exfil.combo: Reads credentials and makes network calls med
dist/tools/pdf/markdown.js:319
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0037 Data from Local SystemMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0025 Exfiltration via Cyber Means
[server desktop-commander] const env = Object.fromEntries(Object.entries(process.env).filter(([name]) => name.toUpperCase() !== 'USERPROFILE'));
What this means: Credential access together with outbound requests in one file is the shape of data theft.
The rule's general advice: Do not install unless the flow is understood and benign. (see the review note for this case)
Known false alarm
A copy of the process environment (minus USERPROFILE) is passed to the Chrome instance the package launches on Windows to render PDFs. It is not sent anywhere else.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
dist/ui/file-preview/shared/preview-file-types.js:39
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
[server desktop-commander] '.env',
What this means: Reads files or environment holding keys, tokens or sessions.
The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)
Known false alarm
'.env' is one entry in a list of file names the file previewer shows as plain text. It does not read credentials.
Reviewed by Claude (AI-assisted review), 2026-11-21
4 low-severity notes (informational, do not affect the result)
plugin.bundled-mcp: Plugin bundles an MCP server low
.claude-plugin/plugin.json
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0010.005 Supply Chain Compromise: AI Agent Tool
plugin bundles MCP server(s): desktop-commander
What this means: The plugin installs additional MCP servers that run code on your machine and are not covered by this layer alone.
What you can do: Review each bundled server as if you were installing it separately.
identity.repo-mismatch: Repository does not match the package name low
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0111 AI Supply Chain Reputation InflationMITRE ATLAS AML.T0074 Masquerading
[server desktop-commander] repository 'DesktopCommanderMCP' shares no word with package name '@wonderwhy-er/desktop-commander'
What this means: A package whose linked repository has an unrelated name may point to someone else's code to look legitimate.
What you can do: Open the repository and confirm it is the real source of this package.
install-script: Runs code at install time low
package.json:45
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesOWASP Agentic ASI05 Unexpected Code Execution (RCE)MITRE ATLAS AML.T0010.001 Supply Chain Compromise: SoftwareMITRE ATLAS AML.T0011.001 User Execution: Malicious Package
[server desktop-commander] npm run build
What this means: Install hooks run automatically with your privileges before you can review anything.
What you can do: Read the script; prefer packages with no install hooks.
credential-access: Touches credentials or secrets low
dist/tools/pdf/markdown.js:319
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
[server desktop-commander] const env = Object.fromEntries(Object.entries(process.env).filter(([name]) => name.toUpperCase() !== 'USERPROFILE'));
What this means: Reads files or environment holding keys, tokens or sessions.
What you can do: Confirm the tool needs this; otherwise do not install.
Dispute this result
Maintainer and think this is wrong? Open a dispute on GitHub with the target id plugin-wonderwhy-er-desktopcommandermcp-plugins-claude-302ad5.