registry / AI-agent capability abuse / pennyrouter / 0.3.18

pennyrouter@0.3.18

Install and manage PennyRouter local coding-agent integrations.

AI Security Review

scanned 11d ago · by lpm-firewall-ai

The source shows agent configuration changes during an explicit user-run install, without an npm lifecycle trigger or a confirmed malicious chain. This is a guarded agent integration capability, so a warning is appropriate.

Static reason

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

Trigger

A user invokes the PennyRouter CLI install command.

Impact

Claude Code receives a PennyRouter statusline integration and launch configuration. No confirmed malicious effect was identified.

Mechanism

The install path configures the Claude Code statusline and persists launch settings; the statusline reads gateway and key values from Claude settings for status requests.

AI rationale

Evidence

src/cli.jssrc/launch.jssrc/statusline.js

Network endpoints1

pennyrouter.com

Decision evidence

public snapshot

AI called this Suspicious at 78.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

The package exposes a CLI and declares no preinstall, install, or postinstall hook.
The CLI dispatches an explicit `install` command to its installer.
The installer configures Claude Code statusline settings and writes a launch settings file.
The statusline code reads Claude settings and derives gateway credentials from their environment block.

Evidence against

The inspected configuration behavior is reached through the explicit CLI install command, not an npm lifecycle hook.
The source describes the statusline request as a gateway status fetch using the configured gateway and key.

Behavioral surface

Source

ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell

Supply chain

HighEntropyStringsUrlStrings

ManifestNo manifest risk signals triggered.

scanned 31 file(s), 350 KB of source, external domains: 127.0.0.1, api.pennyrouter.com, app.example, chatgpt.com, gateway.example, gateway.example.com, gateway.internal.example.com, gw.example, new.example, old.example, opencode.ai, openrouter.example.test, pennyrouter.com, private.example, private.example.test, proxy.example.com, www.perplexity.ai

Source & flagged code

6 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"; ... L47: async function main() { L48: if (!(["darwin", "linux"].includes(process.platform))) { L49: console.log("launch.test.js: skipped on unsupported platform"); ... L53: const root = fs.mkdtempSync(path.join(os.tmpdir(), "pr-launch-test-")); L54: const previous = Object.fromEntries(ENV_KEYS.map((key) => [key, process.env[key]])); L55: const home = path.join(root, "home"); ... L61: }, null, 2)}\n`; L62: const nativeCodex = 'model = "native-model"\n\nmodel_provider = "pennyrouter"\n\n[model_providers.pennyrouter]\nname = "PennyRouter"\nbase_url = "http://localhost:8400/v1"\n'; L63: 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. const claude_desktop_profile_id = "70656e6e-7972-4f75-8465-720000000001"; const claude_desktop_profile_name = "pennyrouter"; const terminal_title_refresh_ms = 1000; const terminal_status_refresh_ms = 15000; export function pennyconfigdir() { if (process.platform === "win32") { return join(process.env.appdata || process.env.localappdata || homedir(), "pennyrouter"); } return join(process.env.xdg_config_home || join(homedir(), ".config"), "pennyrouter"); } export function pennyconfigpath() { return join(pennyconfigdir(), "config.json"); } export function pennydatadir() { if (process.platform === "win32") { return join(process.env.localappdata || process.env.ap

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

src/harnesses/codex.js#virtual:normalized:round1View file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 3

High

Semantic Analysis Limited

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

src/harnesses/codex.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 = 0.806 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

6 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 High4 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/harnesses/codex.js#virtual:normalized:round1

HighPrevious Version Dangerous Deltasrc/cli.js

MediumNetwork

MediumEnvironment Vars

MediumInstall Persistencesrc/launch.test.js

MediumStructural Risk Force Deep Review

LowScripts Present

LowFilesystem

LowHigh Entropy Strings

LowUrl Strings

Affected versions and remediation

This report applies to pennyrouter@0.3.18.

See all versions of pennyrouter for other recorded verdicts.

Review the evidence and your use of pennyrouter@0.3.18 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 19:01:13.508Z (UTC).

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