registry / hippo-memory / 1.58.0

hippo-memory@1.58.0

Memory for AI agents that learns what is wrong and ranks it down. MCP server, hooks for Claude Code, OpenCode and Codex, AGENTS.md instructions for Codex, Cursor, OpenClaw and Pi. SQLite, zero runtime deps.

AI Security Review

scanned 15d ago · by lpm-firewall-ai

The package has an install hook, but the inspected postinstall implementation performs limited repair and prints setup guidance rather than mutating an agent configuration. Agent integration and workspace registration occur through the package's setup flow, and no concrete malicious behavior was established.

Static reason

One or more suspicious static signals were detected.

Trigger

Package installation triggers the postinstall script; agent setup is triggered by the user running hippo init or a hook installation command.

Impact

No malicious impact was established in the inspected source; user-invoked setup integrates Hippo memory with detected coding agents.

Mechanism

The inspected postinstall repairs a previously installed Codex wrapper and prints setup nudges. CLI setup detects installed agent markers, updates existing instruction files, and installs hooks.

AI rationale

Evidence

package.jsonscripts/postinstall.cjsdist/postinstall.jsdist/cli.jsdist/cli/shared.jsdist/hooks.jsdist/scheduler.js

Decision evidence

public snapshot

AI called this Clean at 88.0% confidence as Benign with low false-positive risk.

Evidence for AI clean decision

package.json runs a postinstall script that loads the package's own dist/postinstall.js.
dist/postinstall.js limits install-time work to repairing a previously installed Codex wrapper and printing setup nudges; it does not install new hooks.
Agent instruction files and hooks are installed through the hippo init flow, which detects existing agent markers and patches an existing instruction file.
The package's instruction block describes Hippo memory commands and how to use them.
The OpenCode plugin installer is exposed as a separate function; no malicious behavior is established by its declaration.
The scheduler registers project workspaces and writes its registry as part of application setup.

Evidence against

The inspected capture path scans local Claude project transcripts only when its mayScan option is enabled.
No source inspected established credential theft, unrelated data exfiltration, or a malicious install-time agent configuration write.

Behavioral surface

Source

ChildProcessCrypto

Source & flagged code

8 flagged

package.jsonView file

Lines 21-61json

21 "dist",

22 "!dist/src",

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

24 "dist-ui",

25 "bin",

26 "scripts/postinstall.cjs",

27 "openclaw.plugin.json",

28 "extensions/openclaw-plugin"

29 ],

30 "scripts": {

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

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

33 "dev": "tsc --watch",

34 "pretest": "npm run build",

35 "test": "vitest run",

36 "test:watch": "vitest",

37 "test:delivery-ledger": "vitest run tests/delivery-ledger",

38 "lint": "oxlint",

39 "sbom": "node scripts/sbom.mjs",

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

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

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg · L41

Medium

Ambiguous Install Lifecycle Script

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

package.jsonView on unpkg · L41

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

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

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

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

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

47 "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"

48 },

49 "keywords": [

50 "memory",

51 "agent-memory",

52 "ai-memory",

53 "llm-memory",

54 "long-term-memory",

55 "persistent-memory",

56 "memory-layer",

57 "mcp",

58 "mcp-server",

59 "model-context-protocol",

60 "claude-code",

61 "claude",

dist/embeddings.jsView file

Lines 81-121javascript

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

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

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

84 * 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/scheduler.jsView file

Lines 10-50javascript

10/** Test-only override. Not part of this module's public API surface. */

11export function __setSchedulerFsDeps(overrides) {

12 fsDeps = { ...fsDeps, ...overrides };

13}

14function defaultRegistry() {

dist/cli.jsView file

•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation. console.error(`unknown hook target: ${target ?? '(none)'}`); process.exit(1); } const hook = hooks[target]; const filepath = path.resolve(process.cwd(), hook.file); if (fs.existssync(filepath)) { const existing = fs.readfilesync(filepath, 'utf8'); if (existing.includes(hook_markers.start) && othersblock(existing)) { const owner = hippoblock(existing)?.owner; const whose = owner ? `hippo wrote it for ${owner}` : 'it has been edited, so hippo cannot tell whose it is'; console.log(`left the hippo block in ${hook.file}: ${whose}. delete it by hand if no agent needs it.

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/cli.jsView on unpkg

dist/cli/shared.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/cli/shared.js#virtual:normalized:round1View on unpkg

Source & flagged code

8 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

101// Promise<object> names that honestly without claiming a specific module shape. L102: const _dynImport = new Function('s', 'return import(s)'); L103: /**

Low

Eval

Package source references a known benign dynamic code generation pattern.

dist/embeddings.jsView on unpkg · L101

Findings

4 High6 Medium6 Low

HighInstall Time Lifecycle Scriptspackage.json

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

HighTrigger Reachable Persistencedist/scheduler.js

HighSemantic Analysis Limiteddist/cli/shared.js#virtual:normalized:round1

MediumAmbiguous Install Lifecycle Scriptpackage.json

MediumDynamic Requiredist/rerankers/cross-encoder.js

MediumNetwork

MediumEnvironment Vars

MediumInstall Persistencedist/scheduler.js

MediumStructural Risk Force Deep Review

LowNon Install Lifecycle Scripts

LowScripts Present

LowEvaldist/embeddings.js

Affected versions and remediation

This report applies to hippo-memory@1.58.0.

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

Review the evidence and your use of hippo-memory@1.58.0 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: 2026-10-07 20:27:24.625Z (UTC).

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