registry / AI-agent capability abuse / osborn / 0.9.241

osborn@0.9.241

Voice AI coding assistant - local agent that connects to Osborn frontend

AI Security Review

scanned 25d ago · by lpm-firewall-ai

The package performs concrete global Claude configuration and skill mutations during normal use, which warrants a warning under the agent integration policy. Static inspection found no automatic install-time execution, exfiltration, or destructive behavior supporting a block.

Static reason

High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source

Trigger

The user starts the Osborn agent or sends a skill-add request through its frontend connection.

Impact

These actions can alter Claude agent behavior or make supplied skills available globally, but no confirmed credential export or remote payload execution was found.

Mechanism

Startup imports a module that updates Claude settings; a frontend message can write a skill file, and the recall command conditionally creates a Claude-directory symlink.

AI rationale

Evidence

dist/index.jsdist/claude-llm.jsbin/recall.js~/.claude/settings.json~/.claude/skills/<sanitized-name>/SKILL.md~/.claude

Decision evidence

public snapshot

AI called this Suspicious at 87.0% confidence as Dangerous Capability with low false-positive risk.

Evidence for warning

The package declares command-line binaries and no install lifecycle hook.
The main agent imports the Claude LLM module during startup.
That module changes global Claude settings and invokes the change at module load.
Frontend skill-add requests write user-provided content into the global Claude skills directory; the recall command can also create a Claude-directory symlink.

Evidence against

No preinstall, install, or postinstall hook was found.
No confirmed network exfiltration or destructive action was identified.

Behavioral surface

Source

ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell

Supply chain

HighEntropyStringsUrlStrings

ManifestNo manifest risk signals triggered.

scanned 37 file(s), 1.33 MB of source, external domains: 127.0.0.1, api.groq.com, api.openai.com, api.smithery.ai, cloud.livekit.io, code-server.dev, example.com, openrouter.ai, osborn.app, voice-native.com, www.voice-native.com

Source & flagged code

9 flagged

bin/recall.jsView file

Lines 1-25javascript

1#!/usr/bin/env node

3// osborn-recall — thin shim. Runs src/recall-cli.ts via tsx in dev, or the

4// compiled dist/recall-cli.js after `npm install`. Mirrors bin/cli.js.

6import { spawn } from 'child_process'

7import { fileURLToPath } from 'url'

High

Child Process

Package source references child process execution.

bin/recall.jsView on unpkg · L5

8import { dirname, join } from 'path'

9import { existsSync, lstatSync, symlinkSync } from 'fs'

10import os from 'os'

12// Same /workspace/.claude symlink guard as cli.js so stores resolve on Fly machines.

13try {

14 const home = os.homedir()

15 const target = '/workspace/.claude'

16 const link = join(home, '.claude')

17 if (existsSync(target) && home !== '/workspace') {

18 let needsLink = true

19 try { needsLink = !lstatSync(link).isSymbolicLink() } catch {}

20 if (needsLink) symlinkSync(target, link)

21 }

22} catch {}

24const __dirname = dirname(fileURLToPath(import.meta.url))

25const args = process.argv.slice(2)

dist/jsonl-search.jsView file

Lines 14-54javascript

14import { join } from 'path';

15import { readSessionHistory } from './session-access.js';

16// ============================================================

17// BM25 CACHE

18// ============================================================

19let bm25Cache = null

dist/index.jsView file

Lines 1-22javascript

1// Load environment variables FIRST before any other imports

2import 'dotenv/config';

3// Then hydrate volume-persisted user secrets into process.env, BEFORE any

4// module that reads its keys at load time (recall-client's RECALL_REGION const,

5// claude-auth fallback). Side-effect import — must stay right after dotenv.

6import './boot-secrets.js';

7import { voice, initializeLogger } from '@livekit/agents'

deploy.shView file

•path = deploy.sh kind = build_helper sizeBytes = 2309 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

deploy.shView on unpkg

dist/session-access.js#virtual:normalized:round1View file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 1

High

Semantic Analysis Limited

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

dist/session-access.js#virtual:normalized:round1View on unpkg

Source & flagged code

9 flagged · loading source

bin/recall.jsView file

5L6: import { spawn } from 'child_process' L7: import { fileURLToPath } from 'url'

High

Child Process

Package source references child process execution.

bin/recall.jsView on unpkg · L5

dist/jsonl-search.jsView file

34// @vscode/ripgrep bundles the rg binary — this is our own dependency L35: const { rgPath } = require('@vscode/ripgrep'); L36: if (rgPath && existsSync(rgPath))

Medium

Dynamic Require

Package source references dynamic require/import behavior.

dist/jsonl-search.jsView on unpkg · L34

dist/index.jsView file

2565const which = await new Promise((res) => { L2566: const p = spawn('which', ['code-server']); L2567: let out = ''; ... L2574: await new Promise((res, rej) => { L2575: const install = spawn('sh', ['-c', 'curl -fsSL https://code-server.dev/install.sh | sh'], { L2576: env: { ...process.env }, L2577: stdio: ['ignore', 'pipe', 'pipe'],

Findings

5 Critical3 High5 Medium5 Low

CriticalSame File Env Network Executiondist/index.js

CriticalCredential Exfiltrationdist/index.js

CriticalCommand Output Exfiltrationdist/index.js

CriticalDownload Executedist/index.js

CriticalPrevious Version Dangerous Deltadist/index.js

HighChild Processbin/recall.js

HighShell

HighSemantic Analysis Limiteddist/session-access.js#virtual:normalized:round1

MediumDynamic Requiredist/jsonl-search.js

MediumNetwork

MediumEnvironment Vars

MediumShips Build Helperdeploy.sh

MediumStructural Risk Force Deep Review

Affected versions and remediation

This report applies to osborn@0.9.241.

See all versions of osborn for other recorded verdicts.

Review the evidence and your use of osborn@0.9.241 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: 2026-09-28 08:23:29.630Z (UTC).

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

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Affected versions and remediation

Runtime surface

Behavioral surface

Source & flagged code