owlmem@0.9.2
OwlMem command line: connect your AI apps to OwlMem in one command (npx -y owlmem install), an end-to-end encrypted vault for your AI agents, and a local MCP server.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe package silently reports aggregated Claude Code and Codex usage from local session files while auto-wake is running. Because the README does not disclose this runtime telemetry, warn rather than block; the inspected report contains aggregates rather than prompts or transcript contents.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
The user enables auto-wake; its background process starts reporting after 30 seconds and repeats periodically.
Impact
OwlMem receives activity and quota summaries from local AI sessions without this reporting being described in the README.
Mechanism
The program scans local Claude Code and Codex session files, summarizes usage and status, and posts the summaries to OwlMem.
AI rationale
The package silently reports aggregated Claude Code and Codex usage from local session files while auto-wake is running. Because the README does not disclose this runtime telemetry, warn rather than block; the inspected report contains aggregates rather than prompts or transcript contents.
Evidence
owlmem.mjsREADME.md~/.claude/projects/**/*.jsonl~/.codex/sessions/**/*.jsonl~/.config/owlmem/wake/usage.json
Network endpoints2
owlmem.com/v1/wake/usageapi.anthropic.com/api/oauth/usage
Decision evidence
public snapshotAI called this Suspicious at 89.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- Auto-wake reads Claude Code and Codex session directories from the user's home or configured directories.
- It derives per-day, per-app token usage and status summaries from those session files.
- While auto-wake runs, it periodically sends those summaries to OwlMem at `/v1/wake/usage`; the README does not describe this reporting.
- The reporting runs only when auto-wake has been set up, which requires an explicit enable action.
Evidence against
- The usage report contains aggregates and status fields rather than transcript text or prompts.
- The Claude OAuth token is sent to Anthropic's own usage endpoint, and the source says this happens only when the owner enables quota reading in the console.
- The package's documented purpose includes running an opted-in background auto-wake service.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
Source & flagged code
10 flaggedowlmem.mjsView file
14// owlmem vault ls
L15: // owlmem vault get <name> [field] prints the item (or one field) to stdout
L16: // owlmem vault put <name> [--desc text] < value-or-json
...
L37: import { readFileSync, writeFileSync, mkdirSync, existsSync, chmodSync, copyFileSync, rmSync, statSync, realpathSync, openSync, closeSync, appendFileSync, renameSync, readdirSync, ...
L38: import { gunzipSync } from "node:zlib";
L39: import { homedir, hostname, userInfo } from "node:os";
...
L41: import { fileURLToPath } from "node:url";
L42: import { spawn, spawnSync } from "node:child_process";
L43:
L44: export const VERSION = "0.9.2";
L45: const BASE = (process.env.OWLMEM_URL || "https://owlmem.com").replace(/\/$/, "");
L46: const DIR = process.env.OWLMEM_HOME || join(process.env.XDG_CONFIG_HOME || joi
Critical
Credential Exfiltration
Source appears to send environment or credential material to an external endpoint.
owlmem.mjsView on unpkg · L1414Trigger-reachable chain: manifest.bin -> owlmem.mjs
L14: // owlmem vault ls
L15: // owlmem vault get <name> [field] prints the item (or one field) to stdout
L16: // owlmem vault put <name> [--desc text] < value-or-json
...
L37: import { readFileSync, writeFileSync, mkdirSync, existsSync, chmodSync, copyFileSync, rmSync, statSync, realpathSync, openSync, closeSync, appendFileSync, renameSync, readdirSync, ...
L38: import { gunzipSync } from "node:zlib";
L39: import { homedir, hostname, userInfo } from "node:os";
...
L41: import { fileURLToPath } from "node:url";
L42: import { spawn, spawnSync } from "node:child_process";
L43:
L44: export const VERSION = "0.9.2";
L45: const BASE = (process.env.OWLMEM_URL || "https://owlmem.com").replace(/\/$/, "");
L46: const DIR = process.env.OW
Findings
2 Critical8 High3 Medium3 Low
CriticalCredential Exfiltrationowlmem.mjs
CriticalTrigger Reachable Dangerous Capabilityowlmem.mjs
HighChild Processowlmem.mjs
HighShellowlmem.mjs
HighSame File Env Network Executionowlmem.mjs
HighCommand Output Exfiltrationowlmem.mjs
HighSandbox Evasion Gated Capabilityowlmem.mjs
HighTrigger Reachable Credential Exfiltrationowlmem.mjs
HighTrigger Reachable Command Output Exfiltrationowlmem.mjs
HighSemantic Analysis Limitedowlmem.mjs
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
Affected versions and remediation
This report applies to owlmem@0.9.2.
See all versions of owlmem for other recorded verdicts.
- Review the evidence and your use of owlmem@0.9.2 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: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.