Bawwab: Top 302 scan

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:

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)

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.