Loading npm security reports…

llm-relay@0.70.0: Malicious npm security report (Block) | LPM Firewall

registry / llm-relay / 0.70.0

llm-relay@0.70.0

Loopback bidirectional Anthropic/OpenAI API proxy with tool-call validation and multi-provider routing.

AI Security Review

scanned 3h ago · by lpm-firewall-ai

A global npm install automatically modifies several AI-agent user configuration surfaces. It installs skills and a Codex provider, MCP server, and relay agent that routes tasks through llm-relay.

Static reason

High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review; previous stored version diff introduced dangerous source

Trigger

npm global installation runs postinstall; a failed Codex detector also falls through to provisioning.

Impact

The package can alter host agent behavior and route agent tasks through its local relay without an explicit setup command.

Mechanism

Install-time AI-agent configuration and task-routing injection.

Attack narrative

Installing this package globally invokes its postinstall installer. The installer copies content into multiple AI-agent configuration directories and writes Codex provider, MCP, and relay-agent settings. The generated relay agent requires every task to be dispatched through llm-relay. The Codex detection failure path provisions settings anyway, making the mutation automatic rather than a user-invoked setup action.

Rationale

The automatic postinstall mutation targets broad, foreign AI-agent control surfaces and changes how host agents handle tasks. This meets the install-hook abuse blocking boundary despite the global-install guard.

Evidence

package.jsonscripts/install-skill.mjs~/.claude/skills/llm-relay~/.codex/skills/llm-relay~/.codex/config.toml~/.codex/agents/relay.toml$XDG_CONFIG_HOME/opencode/skills/llm-relay

Source & flagged code

14 flagged · loading source

package.jsonView file

•scripts.postinstall = node scripts/install-skill.mjs || node -e "process.stderr.write('llm-relay: the postinstall hook crashed, so the bundled host skills and Codex setup were NOT fully installed. The p...

Critical

Red Install Lifecycle Script

Install-time lifecycle script matches a deterministic static-gate block pattern.

package.jsonView on unpkg

•scripts.postinstall = node scripts/install-skill.mjs || node -e "process.stderr.write('llm-relay: the postinstall hook crashed, so the bundled host skills and Codex setup were NOT fully installed. The p...

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg

scripts/install-skill.mjsView file

4* shipped source directory, and provision Codex's global provider plus the host-independent MCP L5: * dispatch entry point plus a Codex `relay` subagent file (`~/.codex/agents/relay.toml`) that L6: * pins no model, mirroring `src/setup-claude.ts`'s Claude `relay` agent. ... L9: * so that a repo-local `npm install` (dev checkout, CI) never touches the developer's L10: * ~/.claude, ~/.codex or the XDG config dir. Because the self-updater reinstalls the global L11: * package on a new version, every host's skill description and the missing Codex setup refresh ... L23: */ L24: import { copyFileSync, mkdirSync, existsSync, readFileSync, unlinkSync, writeFileSync } from "node:fs"; L25: import { join, dirname } from "node:path"; ... L60: * subagent docs (`/codex/agent-configuration/subagents`,

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/install-skill.mjsView on unpkg · L4

dist/claude-hook.jsView file

•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation. import { relaystatepath } from "./state-paths.js"; import { existssync, mkdirsync, readfilesync, writefilesync } from "node:fs"; import { join } from "node:path"; import { homedir, tmpdir } from "node:os"; export const agent_hook_filename = "llm-relay-agent-offload.mjs"; export function claudehookpaths(home = homedir()) { if (process.env.vitest && home === homedir()) { const vitesthome = join(tmpdir(), "llm-relay-vitest"); return { settings: join(vitesthome, ".claude", "settings.json"), script: join(vitesthome, "hooks", agent_hook_filename), }; } return { settings: join(home, ".claude", "settings.json"),

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.

dist/claude-hook.jsView on unpkg

dist/config.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.

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

dist/self-update.jsView file

•matchType = normalized_sha256 matchedPackage = llm-relay@0.62.0 matchedPath = dist/self-update.js matchedIdentity = npm:bGxtLXJlbGF5:0.62.0 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.

dist/self-update.jsView on unpkg

dist/lane-quota-probe.jsView file

•matchType = normalized_sha256 matchedPackage = llm-relay@0.62.0 matchedPath = dist/lane-quota-probe.js matchedIdentity = npm:bGxtLXJlbGF5:0.62.0 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.

dist/lane-quota-probe.jsView on unpkg

dist/os-keyring.jsView file

•matchType = normalized_sha256 matchedPackage = llm-relay@0.62.0 matchedPath = dist/os-keyring.js matchedIdentity = npm:bGxtLXJlbGF5:0.62.0 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.

dist/os-keyring.jsView on unpkg

dist/winenv.jsView file

•matchType = normalized_sha256 matchedPackage = llm-relay@0.62.0 matchedPath = dist/winenv.js matchedIdentity = npm:bGxtLXJlbGF5:0.62.0 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.

dist/winenv.jsView on unpkg

scripts/sync-tiers.mjsView file

•matchType = normalized_sha256 matchedPackage = llm-relay@0.62.0 matchedPath = scripts/sync-tiers.mjs matchedIdentity = npm:bGxtLXJlbGF5:0.62.0 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/sync-tiers.mjsView on unpkg

dist/accounting-store-schema.jsView file

•matchType = normalized_sha256 matchedPackage = llm-relay@0.68.5 matchedPath = dist/accounting-store-schema.js matchedIdentity = npm:bGxtLXJlbGF5:0.68.5 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.

dist/accounting-store-schema.jsView on unpkg

dist/dashboard-routes.jsView file

•matchType = normalized_sha256 matchedPackage = llm-relay@0.62.0 matchedPath = dist/dashboard-routes.js matchedIdentity = npm:bGxtLXJlbGF5:0.62.0 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.

dist/dashboard-routes.jsView on unpkg

dist/reshaper.jsView file

•matchType = normalized_sha256 matchedPackage = llm-relay@0.62.0 matchedPath = dist/reshaper.js matchedIdentity = npm:bGxtLXJlbGF5:0.62.0 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.

dist/reshaper.jsView on unpkg

dist/cli.jsView file

•matchType = previous_version_dangerous_delta matchedPackage = llm-relay@0.72.0 matchedIdentity = npm:bGxtLXJlbGF5:0.72.0 similarity = 0.858 summary = stored previous version shares package body but lacks this dangerous source file

Critical

Previous Version Dangerous Delta

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

dist/cli.jsView on unpkg