registry / hippo-memory / 1.45.0

hippo-memory@1.45.0

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 confirms first-party agent hook and plugin setup capabilities, while the inspected postinstall behavior does not establish unconsented agent configuration changes. Classify as suspicious and warn for guarded agent extension lifecycle risk; no concrete malicious behavior was established.

Static reason

One or more suspicious static signals were detected.; source matched previously finalized malicious package; routed for review

Trigger

A user invokes Hippo project initialization or the plugin installation command.

Impact

Agent behavior can be extended by the installed hooks or plugin; no credential theft or unconsented install-time configuration change was established.

Mechanism

CLI setup detects agent files, and the OpenCode installer writes its plugin source at the resolved plugin path.

AI rationale

Evidence

dist/cli.jsdist/hooks.jsdist/hooks.d.tsdist/postinstall.jspackage.jsonscripts/postinstall.cjs

Decision evidence

public snapshot

AI called this Suspicious at 84.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

package.json runs scripts/postinstall.cjs, which loads dist/postinstall.js during installation.
The postinstall code limits Codex repair to an existing wrapper and prints opt-in setup commands; it does not establish first-install agent configuration changes.
CLI initialization can call autoInstallHooks, and its detection covers several agent configuration files.
The exported OpenCode plugin installer resolves a plugin path and writes the package's plugin source there; this is a real agent extension setup capability.
The flagged hooks.js location resolves Codex wrapper paths under the user's home directory; it does not itself show an agent configuration write.
The reviewed excerpts do not establish credential exfiltration or a concrete attack.

Evidence against

Agent hooks and the OpenCode plugin are written through explicit CLI setup paths; the reviewed evidence does not show postinstall invoking the plugin installer.
The inspected Codex postinstall path repairs an existing wrapper and otherwise offers opt-in commands.

Behavioral surface

Source

Source & flagged code

7 flagged

package.jsonView file

Lines 17-57json

17 },

18 "files": [

19 "dist",

20 "!dist/src",

21 "!dist/**/*.map",

22 "dist-ui",

23 "bin",

24 "scripts/postinstall.cjs",

25 "openclaw.plugin.json",

26 "extensions/openclaw-plugin"

27 ],

28 "scripts": {

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

30 "build": "node -e \"require('fs').rmSync('dist',{recursive:true,force:true})\" && tsc && tsc -p tsconfig.benchmarks.json && tsc -p tsconfig.extensions.json",

31 "dev": "tsc --watch",

32 "pretest": "npm run build",

33 "test": "vitest run",

34 "test:watch": "vitest",

35 "lint": "oxlint",

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

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

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg · L37

Medium

Ambiguous Install Lifecycle Script

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

package.jsonView on unpkg · L37

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

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

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

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

42 "version": "node scripts/sync-version.mjs && node scripts/check-manifest-versions.mjs",

43 "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"

44 },

45 "keywords": [

46 "memory",

47 "ai",

48 "agents",

49 "llm",

50 "claude",

51 "context",

52 "recall",

53 "episodic",

54 "semantic",

55 "embeddings",

56 "hybrid-search",

57 "agent-memory",

dist/embeddings.jsView file

Lines 79-119javascript

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

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

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

82 * 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 = 5

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

Source & flagged code

7 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

99// Promise<object> names that honestly without claiming a specific module shape. L100: const _dynImport = new Function('s', 'return import(s)'); L101: /**

Low

Eval

Package source references a known benign dynamic code generation pattern.

dist/embeddings.jsView on unpkg · L99

Findings

4 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

MediumAmbiguous Install Lifecycle Scriptpackage.json

MediumDynamic Requiredist/rerankers/cross-encoder.js

MediumNetwork

MediumEnvironment Vars

MediumStructural Risk Force Deep Review

LowNon Install Lifecycle Scripts

LowScripts Present

LowEvaldist/embeddings.js

LowFilesystem

Low

Affected versions and remediation

This report applies to hippo-memory@1.45.0.

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

Review the evidence and your use of hippo-memory@1.45.0 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 05:44:08.763Z (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