exa
Not malicious, needs a look Reviewed: false alarm
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, 1× ยท first at .vercelignore:24)
- Kind
- Plugin
- Source
- github
- Repository
- exa-labs/exa-mcp-server
- Commit
15ffb50519e719dc791cdc750ce5ed1934c0a1ed- Listed in
- anthropics/claude-plugins-official
- Popularity
- 5,246 GitHub stars (2026-11-20) (official, always included)
- Link
- https://github.com/exa-labs/exa-mcp-server/tree/15ffb50519e719dc791cdc750ce5ed1934c0a1ed
- Scanned
- 2026-11-20T23:17:00+00:00
- Scan time
- 1.7 s
- Scanned as
- plugin
Review note: A normal build step and an ignore-file entry; nothing malicious.
Findings (2)
install-script: Runs code at install time med
package.json:51
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
npm run build:stdio
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)
Known false alarm
The `prepare` script runs the local esbuild build (`build:stdio`) to make dist/stdio.cjs. It downloads and runs nothing remote.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
.vercelignore:24
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
.env.local
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
.vercelignore lists .env.local so local secrets are not uploaded to Vercel. Protective.
Reviewed by Claude (AI-assisted review), 2026-11-21
2 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): exa
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.
fetch.auth-required: Remote server requires sign-in low
[server exa] remote server answered HTTP 403; sign-in required
What this means: The remote server requires sign-in; its tool descriptions could not be read. Bawwab re-checks at session start.
What you can do: Sign in through Claude; Bawwab re-checks the tool descriptions at session start.
Dispute this result
Maintainer and think this is wrong? Open a dispute on GitHub with the target id plugin-exa-labs-exa-mcp-server-671ae8.