registry / warp-agent-mcp / 0.22.0

warp-agent-mcp@0.22.0

MCP server for the Warp freight API, covering the full booking lifecycle: mode compare (one call prices every eligible mode in parallel and returns a decision-complete recommendation with the cost-vs-transit math), quote (van/box-truck/FTL/LTL — LTL split

AI Security Review

scanned 6d ago · by lpm-firewall-ai

The postinstall hook automatically configures a first-party Claude Desktop extension, which leaves a consent risk and warrants a warning. Inspected runtime authentication uses Warp endpoints, and no separate concrete attack behavior was established.

Static reason

High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review

Trigger

Installing the package runs its postinstall script.

Impact

Claude Desktop may start this package as an MCP server after installation, without an explicit setup command from the user.

Mechanism

The script reads Claude Desktop’s configuration, sets the warp server entry to this package’s launcher, and writes the configuration file.

AI rationale

Evidence

package.jsonscripts/postinstall.mjsClaude claude_desktop_config.json

Network endpoints2

customer.wearewarp.comwww.wearewarp.com/api/v1/warp

Decision evidence

public snapshot

AI called this Suspicious at 88.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

The install hook automatically adds this package’s MCP server entry to the user’s Claude Desktop configuration.
The entry launches this package’s own run script; the hook does not show changes to other servers or agent settings.
The launcher and login flow use Warp’s service endpoints for API requests and credentials.

Evidence against

Inspected source shows no credential transfer to an unrelated recipient or broader agent configuration change.

Behavioral surface

Source

ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell

Supply chain

HighEntropyStringsMinifiedUrlStrings

ManifestNo manifest risk signals triggered.

scanned 29 file(s), 1.60 MB of source, external domains: customer.wearewarp.com, json-schema.org, nodejs.org, tracking.wearewarp.com, www.w3.org, www.wearewarp.com

Source & flagged code

9 flagged

package.jsonView file

•scripts.postinstall = node scripts/postinstall.mjs

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg

•scripts.postinstall = node scripts/postinstall.mjs

Medium

Ambiguous Install Lifecycle Script

Install-time lifecycle script is not statically allowlisted and needs review.

package.jsonView on unpkg

scripts/run.mjsView file

9Manifest entrypoint (manifest.bin) carries capability families absent from dist/build output: environment+network, execution+network L9: import { homedir } from "node:os"; L10: import { spawn } from "node:child_process"; L11: import { fileURLToPath } from "node:url"; ... L13: L14: const __dirname = dirname(fileURLToPath(import.meta.url)); L15: // Point at dist/ (built from src/ at version-bump time) instead of the pre-baked ... L22: const homes = [ L23: process.env.HOME, L24: homedir(), ... L30: try { L31: const cfg = JSON.parse(readFileSync(join(h, ".warp", "config.json"), "utf8")); L32: if (cfg.api_key) return cfg.api_key;

High

Entrypoint Build Divergence

Manifest entrypoint contains risky behavior absent from dist/build output.

scripts/run.mjsView on unpkg · L9

•matchType = normalized_sha256 matchedPackage = warp-agent-mcp@0.20.1 matchedPath = scripts/run.mjs matchedIdentity = npm:d2FycC1hZ2VudC1tY3A:0.20.1 similarity = 1.000 summary = normalized source hash matched finalized malicious source

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

scripts/run.mjsView on unpkg

scripts/postinstall.mjsView file

5L6: import { readFileSync, writeFileSync, mkdirSync, existsSync } from "node:fs"; L7: import { join } from "node:path"; ... L77: // Check if already configured correctly L78: const existing = config?.mcpServers?.warp; L79: if (existing?.command === warpEntry.command && ... L85: // Add/update the warp entry L86: config.mcpServers = config.mcpServers || {}; L87: config.mcpServers.warp = warpEntry; L88: L89: try { L90: mkdirSync(configDir, { recursive: true });

Critical

Ai Agent Control Hijack

Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.

scripts/postinstall.mjsView on unpkg · L5

•matchType = normalized_sha256 matchedPackage = warp-agent-mcp@0.20.1 matchedPath = scripts/postinstall.mjs matchedIdentity = npm:d2FycC1hZ2VudC1tY3A:0.20.1 similarity = 1.000 summary = normalized source hash matched finalized malicious source

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

scripts/postinstall.mjsView on unpkg

dist/client.js#virtual:normalized:round1View file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 2

High

Semantic Analysis Limited

A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.

dist/client.js#virtual:normalized:round1View on unpkg

scripts/check-description.mjsView file

•matchType = normalized_sha256 matchedPackage = warp-agent-mcp@0.20.1 matchedPath = scripts/check-description.mjs matchedIdentity = npm:d2FycC1hZ2VudC1tY3A:0.20.1 similarity = 1.000 summary = normalized source hash matched finalized malicious source

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

scripts/check-description.mjsView on unpkg

bin/warp-agent-mcpView file

•matchType = normalized_sha256 matchedPackage = warp-agent-mcp@0.20.1 matchedPath = bin/warp-agent-mcp matchedIdentity = npm:d2FycC1hZ2VudC1tY3A:0.20.1 similarity = 1.000 summary = normalized source hash matched finalized malicious source

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

bin/warp-agent-mcpView on unpkg

Source & flagged code

9 flagged · loading source

package.jsonView file

•scripts.postinstall = node scripts/postinstall.mjs

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg

•scripts.postinstall = node scripts/postinstall.mjs

Medium

Ambiguous Install Lifecycle Script

Install-time lifecycle script is not statically allowlisted and needs review.

package.jsonView on unpkg

scripts/run.mjsView file

High

Entrypoint Build Divergence

Manifest entrypoint contains risky behavior absent from dist/build output.

scripts/run.mjsView on unpkg · L9

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

scripts/run.mjsView on unpkg

scripts/postinstall.mjsView file

Critical

Ai Agent Control Hijack

Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.

scripts/postinstall.mjsView on unpkg · L5

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

scripts/postinstall.mjsView on unpkg

dist/client.js#virtual:normalized:round1View file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 2

High

Semantic Analysis Limited

A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.

dist/client.js#virtual:normalized:round1View on unpkg

scripts/check-description.mjsView file

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

scripts/check-description.mjsView on unpkg

bin/warp-agent-mcpView file

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

bin/warp-agent-mcpView on unpkg

Findings

1 Critical7 High4 Medium5 Low

CriticalAi Agent Control Hijackscripts/postinstall.mjs

HighInstall Time Lifecycle Scriptspackage.json

HighEntrypoint Build Divergencescripts/run.mjs

HighSemantic Analysis Limiteddist/client.js#virtual:normalized:round1

HighKnown Malware Source Similarityscripts/run.mjs

HighKnown Malware Source Similarityscripts/check-description.mjs

HighKnown Malware Source Similarityscripts/postinstall.mjs

HighKnown Malware Source Similaritybin/warp-agent-mcp

MediumAmbiguous Install Lifecycle Scriptpackage.json

MediumNetwork

MediumEnvironment Vars

MediumStructural Risk Force Deep Review

LowNon Install Lifecycle Scripts

LowScripts Present

LowFilesystem

LowHigh Entropy Strings

LowUrl Strings

Affected versions and remediation

This report applies to warp-agent-mcp@0.22.0.

See all versions of warp-agent-mcp for other recorded verdicts.

Review the evidence and your use of warp-agent-mcp@0.22.0 before allowing it. Restrict the permissions described in this report.
Choose an independently verified alternative or release. This report does not establish that other versions are safe.

Evidence last updated: 2026-10-16 20:07:42.521Z (UTC).

Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.