owlmem@0.9.11
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 1d ago · by lpm-firewall-aiThe manifest has no install hooks, and the CLI dispatcher does not run on import. Reviewed credential and background-task flows serve disclosed features and require the relevant user setup or console authorization.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
CLI commands run when invoked. Auto-wake and Claude quota collection require user setup or an owner’s console setting.
Impact
No unauthorized collection or action was identified in the reviewed paths.
Mechanism
OwlMem API requests use the configured OwlMem token. When enabled, Claude Code’s token goes to Anthropic’s usage endpoint; quota figures and disclosed usage metrics go to OwlMem.
AI rationale
The manifest has no install hooks, and the CLI dispatcher does not run on import. Reviewed credential and background-task flows serve disclosed features and require the relevant user setup or console authorization.
Evidence
~/.claude/.credentials.json~/.claude/projects/**/*.jsonl~/.codex/sessions/**/*.jsonl
Network endpoints3
owlmem.comapi.anthropic.com/api/oauth/usage127.0.0.1:<detected-port>/exa.language_server_pb.LanguageServerService/
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest exposes owlmem.mjs as a CLI binary and defines no lifecycle scripts.
- The module calls main() only when invoked as the CLI; importing it does not start the command dispatcher.
- Claude quota collection reads Claude Code’s own OAuth token and is gated on the console-provided read_quota setting.
- The Claude OAuth token is sent to Anthropic’s usage endpoint; OwlMem receives quota percentages and reset times.
- Auto-wake requires explicit setup and pairing approval before it starts AI tasks.
Evidence against
- The package describes itself as an OwlMem CLI for an encrypted vault and AI integrations.
- Usage reporting is documented as sending token counts and status without transcript text or paths.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
10 flaggedowlmem.mjsView file
16// owlmem vault ls
L17: // owlmem vault get <name> [field] prints the item (or one field) to stdout
L18: // owlmem vault put <name> [--desc text] < value-or-json
...
L39: import { readFileSync, writeFileSync, mkdirSync, existsSync, chmodSync, copyFileSync, rmSync, statSync, realpathSync, openSync, closeSync, appendFileSync, renameSync, readdirSync, ...
L40: import { gunzipSync } from "node:zlib";
L41: import { homedir, hostname, userInfo } from "node:os";
...
L43: import { fileURLToPath } from "node:url";
L44: import { spawn, spawnSync } from "node:child_process";
L45:
L46: export const VERSION = "0.9.11";
L47: const BASE = (process.env.OWLMEM_URL || "https://owlmem.com").replace(/\/$/, "");
L48: const DIR = process.env.OWLMEM_HOME || join(process.env.XDG_CONFIG_HOME || jo
Critical
Credential Exfiltration
Source appears to send environment or credential material to an external endpoint.
owlmem.mjsView on unpkg · L1616Trigger-reachable chain: manifest.bin -> owlmem.mjs
L16: // owlmem vault ls
L17: // owlmem vault get <name> [field] prints the item (or one field) to stdout
L18: // owlmem vault put <name> [--desc text] < value-or-json
...
L39: import { readFileSync, writeFileSync, mkdirSync, existsSync, chmodSync, copyFileSync, rmSync, statSync, realpathSync, openSync, closeSync, appendFileSync, renameSync, readdirSync, ...
L40: import { gunzipSync } from "node:zlib";
L41: import { homedir, hostname, userInfo } from "node:os";
...
L43: import { fileURLToPath } from "node:url";
L44: import { spawn, spawnSync } from "node:child_process";
L45:
L46: export const VERSION = "0.9.11";
L47: const BASE = (process.env.OWLMEM_URL || "https://owlmem.com").replace(/\/$/, "");
L48: const DIR = process.env.O
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@0.9.11.
See all versions of owlmem for other recorded verdicts.
- Review the evidence and your use of owlmem@0.9.11 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.