owlmem@0.9.1
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 source sends an OwlMem token to OwlMem's own service by default and gates vault-backed command execution behind a tool call. The command entry point runs only when invoked, and the reviewed network and execution behavior matches the package's stated purpose.
Static reason
One or more suspicious static signals were detected.
Trigger
CLI commands run when invoked; MCP behavior requires starting the server and receiving a tool call.
Impact
The reviewed behavior matches the package's stated vault and AI integration purpose.
Mechanism
The CLI contacts OwlMem or the configured OWLMEM_URL using its OwlMem token. Vault-backed command execution is exposed as a tool and masks matching secret values in captured output.
AI rationale
The source sends an OwlMem token to OwlMem's own service by default and gates vault-backed command execution behind a tool call. The command entry point runs only when invoked, and the reviewed network and execution behavior matches the package's stated purpose.
Evidence
owlmem.mjspackage.json
Network endpoints2
owlmem.comOWLMEM_URL (configurable base URL)
Decision evidence
public snapshotAI called this Clean at 97.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest describes OwlMem as an AI-agent vault CLI and declares owlmem.mjs as its command entry point.
- Network requests use the OwlMem service by default; the base URL can be set with OWLMEM_URL.
- The CLI sends its OwlMem token to that configured base URL for vault requests.
- Vault command execution receives secrets only through an explicit vault_run tool call; command output is masked against those secrets.
- The CLI runs only when invoked as a command, rather than starting its main routine on import.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
7 flaggedowlmem.mjsView file
41import { fileURLToPath } from "node:url";
L42: import { spawn, spawnSync } from "node:child_process";
L43:
High
436inputSchema: { type: "object", properties: {
L437: command: { type: "string", description: "Shell command to run (sh -c)" },
L438: env: { type: "object", description: 'Map of ENV_VAR to "item" or "item:field", e.g. {"DB_PASSWORD": "prod/db:password"}', additionalProperties: { type: "string" } },
High
41import { fileURLToPath } from "node:url";
L42: import { spawn, spawnSync } from "node:child_process";
L43:
L44: export const VERSION = "0.9.1";
L45: const BASE = (process.env.OWLMEM_URL || "https://owlmem.com").replace(/\/$/, "");
L46: const DIR = process.env.OWLMEM_HOME || join(process.env.XDG_CONFIG_HOME || join(homedir(), ".config"), "owlmem");
High
Same File Env Network Execution
A single source file combines environment access, network access, and code or shell execution; review context before blocking.
owlmem.mjsView on unpkg · L41Findings
7 High3 Medium3 Low
HighChild Processowlmem.mjs
HighShellowlmem.mjs
HighSame File Env Network Executionowlmem.mjs
HighCommand Output Exfiltrationowlmem.mjs
HighSandbox Evasion Gated Capabilityowlmem.mjs
HighTrigger Reachable Command Output Exfiltrationowlmem.mjs
HighSemantic Analysis Limitedowlmem.mjs
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to owlmem@0.9.1.
See all versions of owlmem for other recorded verdicts.
- Review the evidence and your use of owlmem@0.9.1 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.