registry / AI-agent capability abuse / hippo-memory / 1.52.7

hippo-memory@1.52.7

Memory for AI agents that learns what is wrong and stops repeating it. MCP server and hooks for Claude Code, Codex and Cursor. SQLite, zero runtime deps.

AI Security Review

scanned 14d ago · by lpm-firewall-ai

Classify as suspicious because the explicit `hippo init` command can modify agent configuration, and static analysis coverage is incomplete. The inspected npm postinstall behavior does not establish unconsented first-time agent setup or another concrete attack.

Static reason

One or more suspicious static signals were detected.

Trigger

A user runs `hippo init` without `--no-hooks`.

Impact

This changes project agent configuration; the inspected path is explicitly user-invoked and does not establish malicious behavior.

Mechanism

The CLI detects agent markers in the current project and patches existing instruction files with Hippo hook instructions.

AI rationale

Evidence

dist/cli.js

Decision evidence

public snapshot

AI called this Suspicious at 78.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

The CLI’s `init` path invokes hook setup unless `--no-hooks` is set.
Hook setup detects agent files in the current project and patches existing instruction files, adding Hippo hook instructions.
The npm `postinstall` script loads the package postinstall module.
The postinstall module repairs a previously installed Codex wrapper and prints setup guidance; it does not perform first-time wrapper installation.
The package’s agent integration behavior is a user-invoked configuration capability, so the reviewed source does not establish an active attack.

Evidence against

The explicit `hippo init` command can modify existing agent instruction files in the current project, making this a real agent-configuration capability.
Static analysis reported parse errors in several files, so a clean classification is not supported by complete analysis coverage.

Behavioral surface

Source

ChildProcessCryptoDynamicRequireEnvironmentVarsEvalFilesystem

Source & flagged code

6 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 "agent-memory",

50 "ai-memory",

51 "llm-memory",

52 "long-term-memory",

53 "persistent-memory",

54 "memory-layer",

55 "mcp",

56 "mcp-server",

57 "model-context-protocol",

58 "claude-code",

59 "claude",

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/cli.jsView file

•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation. detected codex launcher at ${result.commandpath}`); } return; } if (subcommand === 'uninstall') { if (!target || !hooks[target]) { 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}`

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/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

Source & flagged code

6 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

3 High5 Medium6 Low

HighInstall Time Lifecycle Scriptspackage.json

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

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

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

LowHigh Entropy Strings

LowUrl Strings

Affected versions and remediation

This report applies to hippo-memory@1.52.7.

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

Review the evidence and your use of hippo-memory@1.52.7 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 05:44:39.402Z (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