pennyrouter@0.3.57

Install and manage PennyRouter local coding-agent integrations.

AI Security Review

scanned 11d ago · by lpm-firewall-ai

The install-time configuration and later automatic package resolution create a real agent extension lifecycle risk, but the behavior is tied to the package's own MCP integration and is not concrete malicious activity. Recommend a warning rather than a block.

Static reason

One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source

Trigger

A user runs the CLI install flow with MCP registration enabled, then starts a configured harness.

Impact

Future harness startup can resolve and run a package release automatically; no concrete malicious behavior was established in the inspected MCP source.

Mechanism

The CLI writes an MCP command entry for the selected harness that invokes `npx -y pennyrouter mcp`.

AI rationale

Evidence

package.jsonsrc/cli.jssrc/mcp-register.js~/.claude.json~/.codex/config.toml

Decision evidence

public snapshot

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

Evidence for warning

The package has no npm lifecycle hooks; setup starts through its CLI.
The install flow registers an MCP server for selected harnesses unless the user disables MCP registration.
The registration points the harness to `npx -y pennyrouter mcp`, which can run when the harness starts.
The package also installs a managed Claude Code statusline and preserves an existing user command.
The other inspected target locations concern profile paths, local session handling, or test fixtures; they do not establish a separate attack.

Evidence against

The MCP entry runs this package's own `mcp` command, and the source describes it as a Threads integration.
No credential theft, unrelated network recipient, or concrete malicious payload was established from the inspected source.

Behavioral surface

Source

ChildProcessCryptoEnvironmentVarsFilesystemNetworkShellWebSocket

Supply chain

Source & flagged code

7 flagged

src/launch.test.jsView file

1import assert from "node:assert/strict"; L2: import { spawnSync } from "node:child_process"; L3: import fs from "node:fs"; ... L54: async function main() { L55: if (!(["darwin", "linux"].includes(process.platform))) { L56: console.log("launch.test.js: skipped on unsupported platform"); ... L60: const root = fs.mkdtempSync(path.join(os.tmpdir(), "pr-launch-test-")); L61: const previous = Object.fromEntries(ENV_KEYS.map((key) => [key, process.env[key]])); L62: const home = path.join(root, "home"); ... L68: }, null, 2)}\n`; L69: const nativeCodex = 'model = "native-model"\n\nmodel_provider = "pennyrouter"\n\n[model_providers.pennyrouter]\nname = "PennyRouter"\nbase_url = "http://localhost:8400/v1"\n'; L70: fs.writeFileSync(path.join(home, ".claude", "settings.json"), nativeClaude);

Medium

Install Persistence

Source writes installer persistence such as shell profile or service configuration.

src/launch.test.jsView on unpkg · L1

src/harnesses/codegpt.jsView file

1import { spawnSync } from "node:child_process"; L2: ... L52: L53: // The record carries the base URL this install actually wrote, so a private/self-hosted L54: // gateway is named here instead of the hosted default the user never configured. ... L58: console.log(" Open CodeGPT settings and remove or replace the PennyRouter provider:"); L59: console.log(` - Base URL: ${record?.changes?.base_url || "https://api.pennyrouter.com/v1"}`); L60: console.log(" - API Key: pr-..."); ... L66: const commands = L67: process.platform === "darwin" L68: ? [["pbcopy"]] L69: : process.platform === "win32"

High

Sandbox Evasion Gated Capability

Source gates dangerous network, credential, or execution behavior behind CI, host, platform, time, or geo fingerprint checks.

src/harnesses/codegpt.jsView on unpkg · L1

src/statusline.jsView file

•Runtime or CLI code links a write operation to an explicit external AI-agent control path: tatusline (all lines) |] penny segment (penny / penny (sub) // / penny (byok) / penny off). the wrapped statusline's first line gets the penny suffix; // any further lines (e.g. a context bar) pass through verbatim. // never blocks on the network: reads a per-session cache and refreshes it detached. import { readfilesync, mkdirsync, writefilesync, statsync } from "node:fs"; import { spawn, spawnsync } from "node:child_process"; import { join, basename } from "node:path"; import os from "node:os"; const statedir = join( process.env.xdg_state_home || join(os.homedir(), ".local", "state"), "pennyrouter", ); const cachedir = join(statedir, "statusline-cache"); const titlesessionfile = process.env.pe

High

External Ai Agent Control Surface Mutation

Runtime or CLI source writes behavior-bearing configuration into a user or project AI-agent control surface.

src/statusline.jsView on unpkg

src/launch.jsView file

•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation. export function pennydatadir() { if (process.platform === "win32") { return join(process.env.localappdata || process.env.appdata || homedir(), "pennyrouter"); } return join(process.env.xdg_data_home || join(homedir(), ".local", "share"), "pennyrouter"); } export function pennyruntimedir() { return join(pennydatadir(), "runtime"); } export function pennycomparedir() { return join(pennydatadir(), "compare"); } export function pennybindir() { if (process.platform === "win32") return join(pennydatadir(), "bin"); return join(homedir(), ".local", "bin"); } export function pennyshimpath() { return join(pennybindir(), process.platform === "win32" ? "penny.cmd" :

High

Trigger Reachable External Ai Agent Control Surface Mutation

Manifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.

src/launch.jsView on unpkg

standalone/claude-proxy.shView file

•path = standalone/claude-proxy.sh kind = build_helper sizeBytes = 8224 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

standalone/claude-proxy.shView on unpkg

src/mcp-register.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.

src/mcp-register.js#virtual:normalized:round1View on unpkg

src/cli.jsView file

•matchType = previous_version_dangerous_delta matchedPackage = pennyrouter@0.3.17 matchedIdentity = npm:cGVubnlyb3V0ZXI:0.3.17 similarity = 0.613 summary = stored previous version shares package body but lacks this dangerous source file

High

Previous Version Dangerous Delta

This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.

src/cli.jsView on unpkg

Source & flagged code

7 flagged · loading source

src/launch.test.jsView file

Medium

Install Persistence

Source writes installer persistence such as shell profile or service configuration.

src/launch.test.jsView on unpkg · L1

src/harnesses/codegpt.jsView file

Findings

5 High5 Medium4 Low

HighSandbox Evasion Gated Capabilitysrc/harnesses/codegpt.js

HighExternal Ai Agent Control Surface Mutationsrc/statusline.js

HighTrigger Reachable External Ai Agent Control Surface Mutationsrc/launch.js

HighSemantic Analysis Limitedsrc/mcp-register.js#virtual:normalized:round1

HighPrevious Version Dangerous Deltasrc/cli.js

MediumNetwork

MediumEnvironment Vars

MediumInstall Persistencesrc/launch.test.js

MediumShips Build Helperstandalone/claude-proxy.sh

MediumStructural Risk Force Deep Review

LowScripts Present

LowFilesystem

LowHigh Entropy Strings

Affected versions and remediation

This report applies to pennyrouter@0.3.57.

See all versions of pennyrouter for other recorded verdicts.

Review the evidence and your use of pennyrouter@0.3.57 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: 2026-10-11 19:07:48.932Z (UTC).

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