owlmem@0.9.6
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 3d ago · by lpm-firewall-aiThe credential and network behavior supports OwlMem’s documented quota feature and is gated by the owner’s setting. The CLI entry point does not run automatically on import, and no malicious behavior was identified.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
A user enables Claude quota reading in the console and runs the configured OwlMem auto-wake feature.
Impact
The inspected flow uses the credential with its own service and is gated by user configuration; no unrelated credential exfiltration or concealed automatic behavior was found.
Mechanism
The program reads Claude Code’s local OAuth credential and sends it to api.anthropic.com to retrieve quota data; the reported data is then sent through OwlMem’s API.
AI rationale
The credential and network behavior supports OwlMem’s documented quota feature and is gated by the owner’s setting. The CLI entry point does not run automatically on import, and no malicious behavior was identified.
Evidence
~/.claude/.credentials.jsonowlmem.mjs
Network endpoints2
api.anthropic.com/api/oauth/usageowlmem.com
Decision evidence
public snapshotAI called this Clean at 94.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest describes OwlMem as a command-line client for its encrypted vault and declares owlmem.mjs as its executable.
- Claude quota collection is documented as enabled only when the owner turns on “Read Claude quota” in the console.
- The Claude credential is read from Claude Code’s local credentials file and used for Anthropic’s own usage endpoint.
- The quota caller checks both that Claude Code is an enabled client and that read_quota is set before making the request.
- The executable runs main only when invoked as the CLI; importing the module does not itself start the command.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
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 = "0.9.6";
L45: const BASE = (process.env.OWLMEM_URL || "https://owlmem.com").replace(/\/$/, "");
L46: const DIR = process.env.OWLMEM_HOME || join(process.env.XDG_CONFIG_HOME || joi
Critical
Credential Exfiltration
Source appears to send environment or credential material to an external endpoint.
owlmem.mjsView on unpkg · L1414Trigger-reachable chain: manifest.bin -> owlmem.mjs
L14: // owlmem vault ls
L15: // owlmem vault get <name> [field] prints the item (or one field) to stdout
L16: // owlmem vault put <name> [--desc text] < value-or-json
...
L37: import { readFileSync, writeFileSync, mkdirSync, existsSync, chmodSync, copyFileSync, rmSync, statSync, realpathSync, openSync, closeSync, appendFileSync, renameSync, readdirSync, ...
L38: import { gunzipSync } from "node:zlib";
L39: import { homedir, hostname, userInfo } from "node:os";
...
L41: import { fileURLToPath } from "node:url";
L42: import { spawn, spawnSync } from "node:child_process";
L43:
L44: export const VERSION = "0.9.6";
L45: const BASE = (process.env.OWLMEM_URL || "https://owlmem.com").replace(/\/$/, "");
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@0.9.6.
See all versions of owlmem for other recorded verdicts.
- Review the evidence and your use of owlmem@0.9.6 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.