owlmem@0.9.5
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 flagged credential and execution behavior is consistent with the package’s encrypted vault and quota features. The reviewed credential flow sends Claude’s sign-in to Anthropic for quota data only when the owner enables that feature; vault secret actions require approval.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
Users invoke CLI commands or connect an AI app to the local MCP server; quota collection requires owner configuration.
Impact
No unauthorized credential disclosure or unrelated account action was found in the reviewed flows.
Mechanism
Vault requests use the configured OwlMem service. Claude quota reads the local Claude sign-in and sends it to Anthropic’s usage endpoint; returned quota data is reported to OwlMem. Vault secret operations require owner approval.
AI rationale
The flagged credential and execution behavior is consistent with the package’s encrypted vault and quota features. The reviewed credential flow sends Claude’s sign-in to Anthropic for quota data only when the owner enables that feature; vault secret actions require approval.
Network endpoints3
owlmem.comapi.anthropic.com127.0.0.1:<port>
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 an encrypted vault and local MCP server, with no lifecycle scripts.
- Claude credentials are read for quota reporting only when enabled by the owner, and the sign-in is sent to Anthropic’s usage endpoint.
- The MCP tool descriptions say vault secret access requires owner approval; vault_run masks secret values in returned output.
- The executable entrypoint dispatches to the CLI only when run as the package command.
Evidence against
- The CLI reads environment variables and credentials, makes network requests, and can run shell commands, but the reviewed flows serve the vault and quota features.
- Auto-wake can install startup behavior, but it is an explicit setup command that requires pairing and console approval before it starts tasks.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
HighEntropyStrings
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 = "0.9.5";
L45: const BASE = (process.env.OWLMEM_URL || "https://owlmem.com").replace(/\/$/, "");
L46: const DIR = process.env.OWLMEM_HOME || join(process.env.XDG_CONFIG_HOME || joi
Critical
Credential Exfiltration
Source appears to send environment or credential material to an external endpoint.
owlmem.mjsView on unpkg · L1414Trigger-reachable chain: manifest.bin -> owlmem.mjs
L14: // owlmem vault ls
L15: // owlmem vault get <name> [field] prints the item (or one field) to stdout
L16: // owlmem vault put <name> [--desc text] < value-or-json
...
L37: import { readFileSync, writeFileSync, mkdirSync, existsSync, chmodSync, copyFileSync, rmSync, statSync, realpathSync, openSync, closeSync, appendFileSync, renameSync, readdirSync, ...
L38: import { gunzipSync } from "node:zlib";
L39: import { homedir, hostname, userInfo } from "node:os";
...
L41: import { fileURLToPath } from "node:url";
L42: import { spawn, spawnSync } from "node:child_process";
L43:
L44: export const VERSION = "0.9.5";
L45: const BASE = (process.env.OWLMEM_URL || "https://owlmem.com").replace(/\/$/, "");
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@0.9.5.
See all versions of owlmem for other recorded verdicts.
- Review the evidence and your use of owlmem@0.9.5 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.