registry / hippo-memory / 1.44.0

hippo-memory@1.44.0

Biologically-inspired memory for AI agents. Zero runtime deps, SQLite, MCP server, and an opt-in hosted TypeSafe Jev reranker. Decay, retrieval strengthening, consolidation.

AI Security Review

scanned 14d ago · by lpm-firewall-ai

Source inspection shows that the flagged agent configuration changes are reached through the user-invoked init flow, while npm postinstall performs repair for an existing Codex wrapper and prints read-only prompts. The available excerpts do not establish a concrete attack or credential exposure.

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

The package postinstall hook runs on installation; agent hook setup is reached through the hippo init command.

Impact

The explicit init command changes local agent configuration; no concrete malicious impact was identified.

Mechanism

Init detects agent markers and appends a Hippo-marked block to an existing target file. Postinstall invokes wrapper repair and prints prompts.

AI rationale

Evidence

dist/cli.jsdist/postinstall.jsscripts/postinstall.cjs

Decision evidence

public snapshot

AI called this Clean at 90.0% confidence as Benign with medium false-positive risk.

Evidence for AI clean decision

npm postinstall runs a wrapper repair and prints setup prompts; it does not perform first-time agent setup.
The user-invoked init flow detects existing agent markers and appends hook configuration to an existing target file.
The detected targets include Claude Code, Codex, Cursor, OpenClaw, OpenCode, and Pi configuration markers.
The flagged capture excerpt reads Claude project directory entries; it does not establish credential collection or exfiltration.
Provider code defines conventional vendor embedding endpoints; the inspected source did not establish an unrelated credential recipient.
Prediction files map database row fields into records; their inspected excerpts show no attack behavior.

Evidence against

The package has a postinstall hook, but its source repairs a previously opted-in Codex wrapper and prints read-only prompts.
The inspection did not establish unconsented install-time agent configuration changes or a concrete attack chain.

Behavioral surface

Source

ChildProcessCrypto

Source & flagged code

9 flagged

package.jsonView file

Lines 15-55json

15 "bin": {

16 "hippo": "bin/hippo.js"

17 },

18 "files": [

19 "dist",

20 "dist-ui",

21 "bin",

22 "scripts/postinstall.cjs",

23 "openclaw.plugin.json",

24 "extensions/openclaw-plugin"

25 ],

26 "scripts": {

27 "baseline": "npm run build && npm test",

28 "build": "tsc && tsc -p tsconfig.benchmarks.json && tsc -p tsconfig.extensions.json",

29 "dev": "tsc --watch",

30 "pretest": "npm run build",

31 "test": "vitest run",

32 "test:watch": "vitest",

33 "lint": "oxlint",

34 "audit:security": "npm audit --audit-level=high && npm --prefix ui audit --audit-level=high",

35 "postinstall": "node scripts/postinstall.cjs",

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg · L35

Medium

Ambiguous Install Lifecycle Script

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

package.jsonView on unpkg · L35

36 "smoke:pack": "node scripts/smoke-pack.mjs",

37 "smoke:openclaw-install": "node scripts/smoke-openclaw-install.mjs",

38 "build:ui": "cd ui && npm install && npm run build",

39 "build:all": "npm run build && npm run build:ui",

40 "prepublishOnly": "node scripts/check-manifest-versions.mjs && node scripts/changelog-fragments.mjs check && node scripts/check-em-dashes-in-release-notes.mjs && node scripts/check-graph-writes.mjs && npm run build:all && node scripts/check-openclaw-dist.mjs && npm run smoke:openclaw-install && node scripts/check-tests-pass.mjs"

41 },

42 "keywords": [

43 "memory",

44 "ai",

45 "agents",

46 "llm",

47 "claude",

48 "context",

49 "recall",

50 "episodic",

51 "semantic",

52 "embeddings",

53 "hybrid-search",

54 "agent-memory",

55 "long-term-memory",

dist/embeddings.jsView file

Lines 78-118javascript

78 * official inference code in `FlagEmbedding`); MiniLM and most sentence-

79 * transformers models use mean pooling. Unknown model ids default to mean

80 * — that is the safe choice because most third-party models adopt the

81 * sentence-transformers convention, and the

dist/rerankers/cross-encoder.jsView file

Lines 1-23javascript

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

2import { pathToFileURL } from 'node:url';

3const MODEL_NAME = 'Xenova/ms-marco-MiniLM-L-6-v2';

4const _require

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@1.40.0 matchedIdentity = npm:aGlwcG8tbWVtb3J5:1.40.0 similarity = 0.800 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/embeddings.jsView file

98// Promise<object> names that honestly without claiming a specific module shape. L99: const _dynImport = new Function('s', 'return import(s)'); L100: /**

Low

Eval

Package source references a known benign dynamic code generation pattern.

dist/embeddings.jsView on unpkg · L98

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/rerankers/cross-encoder.js

MediumNetwork

MediumEnvironment Vars

MediumStructural Risk Force Deep Review

LowNon Install Lifecycle Scripts

Affected versions and remediation

This report applies to hippo-memory@1.44.0.

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

Review the evidence and your use of hippo-memory@1.44.0 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: 2026-10-09 05:44:34.492Z (UTC).

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