hippo-memory@1.40.0

Biologically-inspired memory system for AI agents. Decay by default, strength through use.

AI Security Review

scanned 1mo ago · by lpm-firewall-ai

This is a guarded AI-agent integration with persistence-like repair behavior, so it warrants a warning. The inspected code makes initial integration user-invoked and does not establish concrete malware behavior.

Static reason

One or more suspicious static signals were detected.; source matched previously finalized malicious package; routed for review; previous stored version diff introduced dangerous source

Trigger

Run hippo hook install or hippo setup; a later npm postinstall runs if wrapper metadata already exists.

Impact

Configured agent events execute Hippo commands and the wrapper captures local Codex session data for the package store.

Mechanism

Agent-hook installation and guarded launcher-wrapper repair.

AI rationale

Evidence

package.jsondist/postinstall.jsdist/hooks.jsdist/cli.js~/.claude/settings.json~/.config/opencode/plugins/hippo.ts~/.hippo/integrations/codex.jsondetected Codex launcher

Decision evidence

public snapshot

AI called this Suspicious at 86.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

The package runs a postinstall loader automatically.
Postinstall conditionally repairs an existing Codex launcher wrapper.
Explicit commands can replace a detected Codex launcher and save wrapper metadata.
Explicit setup installs AI-agent commands into Claude Code settings and an OpenCode plugin.

Evidence against

The first wrapper installation is gated behind an explicit CLI command.
The lifecycle path only repairs a wrapper when prior metadata exists.
No runtime dependency or self-dependency is declared.
Network embedding calls use configured provider keys and known provider endpoints.

Behavioral surface

Source

ChildProcessCryptoDynamicRequireEnvironmentVarsEvalFilesystemNetworkShell

Supply chain

HighEntropyStringsMinifiedUrlStrings

Manifest

Source & flagged code

9 flagged

package.jsonView file

•scripts.postinstall = node scripts/postinstall.cjs

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg

•scripts.postinstall = node scripts/postinstall.cjs

Medium

Ambiguous Install Lifecycle Script

Install-time lifecycle script is not statically allowlisted and needs review.

package.jsonView on unpkg

dist/rerankers/cross-encoder.jsView file

Lines 1-29javascript

1import { createRequire } from 'node:module';

2const MODEL_NAME = 'Xenova/ms-marco-MiniLM-L-6-v2';

3// Use Function constructor to bypass TypeScript static module resolution

4// for optional peer dependencies that may not be installed (mirrors the

5// pattern in src/embeddings.ts).

6// SAFETY: this declares the contract we require from the dynamically

7// imported package (a `pipeline` factory, top-level or under `default`);

8// loadTransformersModule validates the resolved value is callable via

9// isPipelineFactory before it is ever invoked.

10const _dynImport = new Function('s', 'return import(s)');

11const _require = createRequire(import.meta.url);

Low

Eval

Package source references a known benign dynamic code generation pattern.

dist/rerankers/cross-encoder.jsView on unpkg · L9

12const TRANSFORMERS_PACKAGES = ['@huggingface/transformers', '@xenova/transformers'];

13function resolveTransformersPackage() {

14 for (const name of TRANSFORMERS_PACKAGES) {

15 try {

16 _require.resolve(name);

17 return name;

18 }

19 catch {

20 // Try the legacy fallback only when the preferred package is not installed.

21 }

22 }

23 return null;

24}

25function isPipelineFactory(value) {

26 return typeof value === 'function';

27}

28async function loadTransformersModule() {

29 // Import one backend only. Loading both native ONNX runtimes in one process

dist/db.jsView file

Lines 1-28javascript

1import * as fs from 'fs';

2import * as os from 'os';

3import * as path from

dist/hooks.jsView file

•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation. } } } return out; } function [redacted](historypath, startoffsetbytes) { if (!fs.existssync(historypath)) return []; const raw = fs.readfilesync(historypath); if (startoffsetbytes >= raw.length) return []; const delta = raw.subarray(startoffsetbytes).tostring('utf8'); const seen = new set(); const ordered = []; for (const line of delta.split('\n')) { if (!line.trim()) continue; try { const parsed = json.parse(line); const sessionid = parsed.session_id; if (isjsonstring(sessionid) && sessionid && !seen.has(sessionid)) { seen.add(sessionid);

High

Trigger Reachable External Ai Agent Control Surface Mutation

Manifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.

dist/hooks.jsView on unpkg

dist/embedding-provider.js#virtual:normalized:round1View file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 9

High

Semantic Analysis Limited

A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.

dist/embedding-provider.js#virtual:normalized:round1View on unpkg

dist/predictions.jsView file

•matchType = normalized_sha256 matchedPackage = hippo-memory@1.24.0 matchedPath = dist/predictions.js matchedIdentity = npm:aGlwcG8tbWVtb3J5:1.24.0 similarity = 1.000 summary = normalized source hash matched finalized malicious source

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

dist/predictions.jsView on unpkg

dist/src/predictions.jsView file

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

dist/src/predictions.jsView on unpkg

dist/cli.jsView file

•matchType = previous_version_dangerous_delta matchedPackage = hippo-memory@1.39.0 matchedIdentity = npm:aGlwcG8tbWVtb3J5:1.39.0 similarity = 0.950 summary = stored previous version shares package body but lacks this dangerous source file

High

Previous Version Dangerous Delta

This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.

dist/cli.jsView on unpkg

Source & flagged code

9 flagged · loading source

package.jsonView file

•scripts.postinstall = node scripts/postinstall.cjs

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg

•scripts.postinstall = node scripts/postinstall.cjs

Medium

Ambiguous Install Lifecycle Script

Install-time lifecycle script is not statically allowlisted and needs review.

package.jsonView on unpkg

dist/rerankers/cross-encoder.jsView file

9// isPipelineFactory before it is ever invoked. L10: const _dynImport = new Function('s', 'return import(s)'); L11: const _require = createRequire(import.meta.url);

Low

Eval

Package source references a known benign dynamic code generation pattern.

dist/rerankers/cross-encoder.jsView on unpkg · L9

Findings

6 High5 Medium6 Low

HighInstall Time Lifecycle Scriptspackage.json

HighTrigger Reachable External Ai Agent Control Surface Mutationdist/hooks.js

HighSemantic Analysis Limiteddist/embedding-provider.js#virtual:normalized:round1

HighKnown Malware Source Similaritydist/predictions.js

HighKnown Malware Source Similaritydist/src/predictions.js

HighPrevious Version Dangerous Deltadist/cli.js

MediumAmbiguous Install Lifecycle Scriptpackage.json

MediumDynamic Requiredist/db.js

MediumNetwork

MediumEnvironment Vars

MediumStructural Risk Force Deep Review

LowNon Install Lifecycle Scripts

Low

Affected versions and remediation

This report applies to hippo-memory@1.40.0.

See all versions of hippo-memory for other recorded verdicts.

Review the evidence and your use of hippo-memory@1.40.0 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: 2026-09-14 14:08:58.738Z (UTC).

Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Affected versions and remediation

Runtime surface

Behavioral surface

Source & flagged code