registry / AI-agent capability abuse / osborn / 0.9.244

osborn@0.9.244

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

AI Security Review

scanned 23d ago · by lpm-firewall-ai

The source establishes explicit-command agent configuration mutation, which the supplied policy classifies as a warning. No npm installation trigger or concrete malicious chain supports blocking.

Static reason

High-risk behavior combination matched malicious policy.

Trigger

Launching osborn loads the settings mutation; receiving a skill_add frontend command activates skill installation.

Impact

Changes affect Claude compaction, session retention, and instructions available to subsequent agent sessions.

Mechanism

The runtime merges settings into the user's Claude configuration and writes frontend-supplied skill content into the home skill directory.

AI rationale

The source establishes explicit-command agent configuration mutation, which the supplied policy classifies as a warning. No npm installation trigger or concrete malicious chain supports blocking.

Evidence

bin/cli.jsdist/index.jsdist/claude-llm.js.claude/settings.json.claude/skills

Decision evidence

public snapshot

AI called this Suspicious at 92.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

The CLI launches dist/index.js, which imports dist/claude-llm.js.
Module loading automatically writes global Claude settings, changing compaction and session retention.
Frontend skill_add commands write supplied content into global Claude skill files.
Frontend commands are activated through received user-input messages.
package.json has no preinstall, install, or postinstall hook.

Evidence against

The behavior runs through the explicitly launched assistant, rather than npm installation.
The inspected authentication fallback uses an OpenRouter key for OpenRouter; it does not establish credential theft.

Behavioral surface

Source

ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell

Supply chain

HighEntropyStringsUrlStrings

ManifestNo manifest risk signals triggered.

Source & flagged code

8 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

8 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

2575const which = await new Promise((res) => { L2576: const p = spawn('which', ['code-server']); L2577: let out = ''; ... L2584: await new Promise((res, rej) => { L2585: const install = spawn('sh', ['-c', 'curl -fsSL https://code-server.dev/install.sh | sh'], { L2586: env: { ...process.env }, L2587: stdio: ['ignore', 'pipe', 'pipe'],

Findings

4 Critical3 High5 Medium5 Low

CriticalSame File Env Network Executiondist/index.js

CriticalCredential Exfiltrationdist/index.js

CriticalCommand Output Exfiltrationdist/index.js

CriticalDownload Executedist/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

LowNon Install Lifecycle Scripts

LowScripts Present

Affected versions and remediation

This report applies to osborn@0.9.244.

See all versions of osborn for other recorded verdicts.

Review the evidence and your use of osborn@0.9.244 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: 2026-09-30 05:00:40.754Z (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