chrome-devtools-mcp
Flagged as possibly malicious Reviewed: expected behaviour
Bawwab's static rules matched a pattern it treats as critical. Read the review notes: a reviewed false alarm is marked as such.
Why it was flagged
The static rules marked this “Flagged as possibly malicious” because of:
obfuscation.eval-decoded: Evaluates decoded content (critical, 1× · first at tests/fixtures/example.heapsnapshot:8)
- Kind
- Plugin
- Source
- github
- Repository
- ChromeDevTools/chrome-devtools-mcp
- Commit
a878bcad39584337e055778353246820deafa7c0- Listed in
- anthropics/claude-plugins-official
- Popularity
- 58,449 GitHub stars (2026-11-20) (official, always included)
- Link
- https://github.com/ChromeDevTools/chrome-devtools-mcp/tree/a878bcad39584337e055778353246820deafa7c0
- Scanned
- 2026-11-20T23:05:42+00:00
- Scan time
- 68.9 s
- Scanned as
- plugin
Review note: Google's Chrome DevTools MCP server; the flagged items are a build-time prepare script, eval scripts that pass the environment to a local child, and test fixtures.
Findings (5)
install-script: Runs code at install time med
package.json:30
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
node scripts/prepare.ts
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 npm prepare script runs scripts/prepare.ts, which patches a type declaration in node_modules and sparse-clones the devtools-frontend submodule from github.com/ChromeDevTools; this runs for developers building the repo.
Reviewed by Bawwab maintainers, 2026-11-20
exfil.combo: Reads credentials and makes network calls med
scripts/eval_gemini.ts:103
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
Object.entries(process.env).forEach(([key, value]) => {
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)
Expected for what this tool does
The eval script copies its own environment into the env of the local MCP server process it starts over stdio and sets CHROME_DEVTOOLS_MCP_NO_USAGE_STATISTICS; nothing is sent over the network by this code.
Reviewed by Bawwab maintainers, 2026-11-20
exfil.combo: Reads credentials and makes network calls med
scripts/profile/profile_mcp.ts:108
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
for (const [key, value] of Object.entries(process.env)) {
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)
Expected for what this tool does
The profiling script copies its environment into the env of the local MCP server it launches over stdio and sets the no-usage-statistics flag; nothing is sent anywhere by this code.
Reviewed by Bawwab maintainers, 2026-11-20
obfuscation.eval-decoded: Evaluates decoded content critical
tests/fixtures/example.heapsnapshot:8
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesOWASP Agentic ASI05 Unexpected Code Execution (RCE)MITRE ATLAS AML.T0123 Obfuscated Files or InformationCWE CWE-912 Hidden Functionality
"strings":["<dummy>","","(GC roots)","(Bootstrapper)","(Builtins)","(Client heap)","(Code flusher)","(Compilation cache)","(Debugger)","(Extensions)","(Eternal handles)","(External strings)","(Global
What this means: Decoding then executing a string is a standard way to hide a payload.
The rule's general advice: Replace with plain code; treat the package as hostile. (see the review note for this case)
Known false alarm
The file is a 2.3 MB V8 heap snapshot test fixture; the matched text is just a string table of JavaScript property names such as eval and atob, not code that runs.
Reviewed by Bawwab maintainers, 2026-11-20
exfil.host: References an exfiltration-style host high
tests/utils/url.test.ts:68
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0025 Exfiltration via Cyber Means
assert.strictEqual(isLocalhost('http://128.0.0.1'), false);
What this means: Paste, webhook and tunnel services are commonly used to receive stolen data.
The rule's general advice: Remove or justify the destination. (see the review note for this case)
Known false alarm
This is a unit test asserting that isLocalhost() returns false for non-local addresses like 128.0.0.1; no connection is made.
Reviewed by Bawwab maintainers, 2026-11-20
9 low-severity notes (informational, do not affect the result)
files.binary-unscanned: Binary files not analysed low
1 binary file not analysed; use --deep to run in the sandbox
What this means: Prebuilt executables cannot be read by static rules, so what they do is unknown until they run.
What you can do: Use --deep to run the package in the sandbox, or prefer packages built from source.
credential-access: Touches credentials or secrets low
scripts/eval_gemini.ts:103
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
Object.entries(process.env).forEach(([key, value]) => {
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.
credential-access: Touches credentials or secrets low
scripts/profile/profile_mcp.ts:108
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
for (const [key, value] of Object.entries(process.env)) {
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.
credential-access: Touches credentials or secrets low
tests/shutdown.test.ts:37
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
...process.env,
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.
credential-access: Touches credentials or secrets low
tests/e2e/telemetry.test.ts:184
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
...process.env,
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.
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): chrome-devtools
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.
plugin.bundled-mcp: Plugin bundles an MCP server low
.cursor-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): chrome-devtools
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.
plugin.bundled-mcp: Plugin bundles an MCP server low
.github/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): chrome-devtools
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.
install-script: Runs code at install time low
package.json:30
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 chrome-devtools] node scripts/prepare.ts
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.
Dispute this result
Maintainer and think this is wrong? Open a dispute on GitHub with the target id plugin-chromedevtools-chrome-devtools-mcp-db4496.