owlmem@0.7.7
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 8d ago · by lpm-firewall-aiThe inspected package has no lifecycle hook, and its vault token requests target the configurable service base, which defaults to OwlMem. The MCP vault_run tool exposes caller-supplied shell execution with vault values, so it warrants a dangerous-capability warning without establishing malicious behavior.
Static reason
One or more suspicious static signals were detected.
Trigger
A connected MCP client invokes vault_run.
Impact
A command can transmit or transform injected vault values; output masking does not restrict what the subprocess does.
Mechanism
The tool resolves requested vault items, starts sh -c with the supplied command, and returns output after masking exact secret strings.
AI rationale
The inspected package has no lifecycle hook, and its vault token requests target the configurable service base, which defaults to OwlMem. The MCP vault_run tool exposes caller-supplied shell execution with vault values, so it warrants a dangerous-capability warning without establishing malicious behavior.
Evidence
owlmem.mjs
Network endpoints1
owlmem.com
Decision evidence
public snapshotAI called this Suspicious at 86.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The manifest exposes a CLI entry point and contains no lifecycle hook.
- Vault authentication uses OWLMEM_TOKEN or the saved config token, sends it to BASE, and defaults BASE to https://owlmem.com; the MCP branch is reached when the user runs the CLI with the mcp command.
- The MCP server exposes vault_run. It places selected vault values in the environment of caller-supplied shell code and returns the command output with exact-value masking.
- Other flagged excerpts resolve to vault key, item, and auto-start helper code; they do not establish a separate credential recipient.
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 = "0.7.7";
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@0.7.7.
See all versions of owlmem for other recorded verdicts.
- Review the evidence and your use of owlmem@0.7.7 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.