registry / AI-agent capability abuse / hippo-memory / 1.52.2

hippo-memory@1.52.2

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

The install lifecycle is limited to repair of an existing opted-in Codex wrapper and visible setup prompts. Explicit `hippo init` can mutate agent configuration, which warrants a warning under the user-command setup policy, but the inspected source does not establish malicious behavior.

Static reason

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

Trigger

A user runs `hippo init` in a project with recognized agent configuration.

Impact

Agent sessions may invoke Hippo integration code after setup. The inspected sources do not establish credential theft, exfiltration, or another concrete attack.

Mechanism

The CLI detects configured agents and writes hook configuration or the Hippo OpenCode plugin; the package postinstall path only repairs a previously opted-in Codex wrapper and prints setup guidance.

AI rationale

Evidence

dist/cli.jsdist/hooks.jsdist/postinstall.js

Decision evidence

public snapshot

AI called this Suspicious at 89.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

The install hook runs a postinstall script, whose package entry delegates to dist/postinstall.js.
The postinstall path repairs a Codex wrapper only for users who previously opted in; otherwise it prints setup instructions.
Running `hippo init` can detect existing agent configuration and install Hippo hooks or a plugin into it.
The OpenCode plugin installer writes the package’s plugin source under the resolved plugin path.

Evidence against

The inspected install path does not perform first-time agent integration; its Claude and Codex messages direct users to explicit setup commands.
The flagged capture code reads Claude project transcript paths; the cited section does not show credential collection or network transmission.

Behavioral surface

Source

ChildProcessCryptoDynamicRequireEnvironmentVarsEvalFilesystemNetworkShell

Supply chain

HighEntropyStrings

Source & flagged code

7 flagged

package.jsonView file

Lines 19-59json

19 "files": [

20 "dist",

21 "!dist/src",

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

23 "dist-ui",

24 "bin",

25 "scripts/postinstall.cjs",

26 "openclaw.plugin.json",

27 "extensions/openclaw-plugin"

28 ],

29 "scripts": {

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

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

32 "dev": "tsc --watch",

33 "pretest": "npm run build",

34 "test": "vitest run",

35 "test:watch": "vitest",

36 "lint": "oxlint",

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

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

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

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg · L39

Medium

Ambiguous Install Lifecycle Script

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

package.jsonView on unpkg · L39

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

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

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

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

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

45 "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"

46 },

47 "keywords": [

48 "memory",

49 "ai",

50 "agents",

51 "llm",

52 "claude",

53 "context",

54 "recall",

55 "episodic",

56 "semantic",

57 "embeddings",

58 "hybrid-search",

59 "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@1.52.2.

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

Review the evidence and your use of hippo-memory@1.52.2 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 05:43:34.576Z (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