registry / agentic-cortex / 7.1.0

agentic-cortex@7.1.0

⚠ Under review

Persistent self-improving agent memory with tree-of-thoughts reasoning: MCTS/beam search, PRM step verification, self-consistency voting, s1 budget forcing, REPL program-aided reasoning, reflexion self-correction, failure classification, experience replay

Static Scan Results

scanned 19d ago · by rust-scanner

Static analysis completed at 0.0% confidence. No malicious behavior was detected; 22 low-signal pattern(s) were surfaced and cleared.

Static reason

Automated AI review exhausted its retry budget. This package remains unresolved and must not warn or block users.

Decision evidence

public snapshot

Behavioral surface

Source

ChildProcessCryptoEnvironmentVarsEvalFilesystemNetworkShell

Supply chain

HighEntropyStringsUrlStrings

ManifestNo manifest risk signals triggered.

scanned 53 file(s), 1.28 MB of source, external domains: 127.0.0.1, addyosmani.com, agenticai-flow.com, arxiv.org, developersdigest.substack.com, docs.cursor.com, docs.github.com, every.to, github.com, support.claude.com, www.anthropic.com, www.confluent.io

Source & flagged code

15 flagged

package.jsonView file

Lines 12-43json

12 "semantic-memory"

13 ],

14 "license": "MIT",

15 "author": "zallauddin",

16 "bin": {

17 "agentic-cortex": "cli.js",

18 "agentic-cortex-mcp": "src/mcp/server.js"

19 },

20 "main": "cli.js",

21 "dependencies": {

22 "better-sqlite3": "^12.11.1"

23 },

24 "optionalDependencies": {

25 "@xenova/transformers": "^2.17.2"

26 },

27 "engines": {

28 "node": ">=18"

29 },

30 "scripts": {

31 "test": "node --test tests/*.test.js",

32 "postinstall": "node scripts/auto-setup.js",

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg · L32

33 "dashboard": "node cli.js serve"

34 },

35 "files": [

36 "cli.js",

37 "src/",

38 "scripts/",

39 "templates/",

40 "README.md"

41 ]

42}

src/core/hooks.jsView file

Lines 165-205javascript

165 break;

166 }

167 }

168}

169

170/**

171 * Evaluate a condition against observation/context.

172 */

173function evaluateCondition(type, value, observation, context) {

174 switch (type) {

175 case 'type_equals':

176 return observation.type === value;

177 case 'tag_contains':

178 try { return JSON.parse(observation.tags || '[]').includes(value); } catch { return false; }

179 case 'importance_gte':

180 return observation.importance >= parseInt(value, 10);

181 case 'project_equals':

182 return observation.project_path === value;

183 case 'custom_js':

184 // SECURITY: only allow if explicitly enabled via env

185 if (process.env.AGENTIC_CORTEX_HOOKS_JS !== '1') return false;

186 try { return new Function('obs', 'ctx', value)(observation, context); } catch { return false; }

187 default:

Low

Eval

Package source references a known benign dynamic code generation pattern.

src/core/hooks.jsView on unpkg · L185

188 return true;

189 }

190}

191

192/**

193 * Simple template interpolation: {{field}} -> value from observation or context.

194 */

195function interpolate(str, observation, context) {

196 if (!str) return '';

197 return str.replace(/\{\{(\w+)\}\}/g, (_, key) => {

198 if (observation[key] !== undefined) return observation[key];

199 if (context && context[key] !== undefined) return context[key];

200 return '';

201 });

202}

203

204/**

205 * Persist a hook definition to the database.

scripts/create-discovery-files.jsView file

Lines 1-25javascript

1#!/usr/bin/env node

2/**

3 * create-discovery-files.js — Shared module for creating multi-agent discovery files.

4 *

5 * Creates files that various AI coding agents automatically read at session start:

6 * - AGENTS.md (OpenCode, Claude Code — canonical MCP-first discovery)

7 * - .claude/CLAUDE.md (Claude Code)

8 * - .cursor/rules/agentic-cortex.mdc (Cursor, alwaysApply: true)

9 * - .opencode/agentic-cortex.md (OpenCode / Codebuff)

10 *

11 * Also creates MCP server configuration files:

12 * - .mcp.json (Claude Code)

13 * - .cursor/mcp.json (Cursor)

14 * - opencode.json (OpenCode)

15 *

Critical

Ai Agent Control Hijack

Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.

scripts/create-discovery-files.jsView on unpkg · L5

16 * Each file contains self-contained, token-dense instructions

17 * optimized for LLM consumption — not human readability.

18 *

19 * Used by:

20 * - cli.js (setup command)

21 * - scripts/auto-setup.js (postinstall hook)

22 *

23 * @module scripts/create-discovery-files

24 */

•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation. , 'agents.md'); const result = writesection(agentspath, agentsmdcontent); if (result !== 'unchanged') created.push('agents.md'); } catch (err) { console.error('[agentic-cortex] agents.md skipped: ' + err.message); } try { const claudedir = path.join(projectdir, '.claude'); if (!fs.existssync(claudedir)) fs.mkdirsync(claudedir, { recursive: true }); const claudemdcontent = [ '<agentic_cortex>', 'agentic-cortex is installed. persistent, self-improving memory across sessions.', 'mcp server is configured in .mcp.json — ' + mcp_tool_count + ' too

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.

scripts/create-discovery-files.jsView on unpkg

scripts/cortex-hook.shView file

•path = scripts/cortex-hook.sh kind = build_helper sizeBytes = 7908 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

scripts/cortex-hook.shView on unpkg

src/core/code-index.js#virtual:normalized:round1View file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 2

High

Semantic Analysis Limited

A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.

src/core/code-index.js#virtual:normalized:round1View on unpkg

cli.jsView file

•matchType = normalized_sha256 matchedPackage = agentic-cortex@7.2.0 matchedPath = cli.js matchedIdentity = npm:YWdlbnRpYy1jb3J0ZXg:7.2.0 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.

cli.jsView on unpkg

scripts/import-community-knowledge.jsView file

•matchType = normalized_sha256 matchedPackage = agentic-cortex@7.2.0 matchedPath = scripts/import-community-knowledge.js matchedIdentity = npm:YWdlbnRpYy1jb3J0ZXg:7.2.0 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.

scripts/import-community-knowledge.jsView on unpkg

scripts/seed-memory-repo.jsView file

•matchType = normalized_sha256 matchedPackage = agentic-cortex@7.2.0 matchedPath = scripts/seed-memory-repo.js matchedIdentity = npm:YWdlbnRpYy1jb3J0ZXg:7.2.0 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.

scripts/seed-memory-repo.jsView on unpkg

src/core/failure-classifier.jsView file

•matchType = normalized_sha256 matchedPackage = agentic-cortex@7.2.0 matchedPath = src/core/failure-classifier.js matchedIdentity = npm:YWdlbnRpYy1jb3J0ZXg:7.2.0 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.

src/core/failure-classifier.jsView on unpkg

scripts/auto-setup.jsView file

•matchType = normalized_sha256 matchedPackage = agentic-cortex@7.2.0 matchedPath = scripts/auto-setup.js matchedIdentity = npm:YWdlbnRpYy1jb3J0ZXg:7.2.0 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.

scripts/auto-setup.jsView on unpkg

scripts/inject-memory.mjsView file

•matchType = normalized_sha256 matchedPackage = agentic-cortex@7.2.0 matchedPath = scripts/inject-memory.mjs matchedIdentity = npm:YWdlbnRpYy1jb3J0ZXg:7.2.0 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.

scripts/inject-memory.mjsView on unpkg

src/core/repl-executor.jsView file

•matchType = normalized_sha256 matchedPackage = agentic-cortex@7.2.0 matchedPath = src/core/repl-executor.js matchedIdentity = npm:YWdlbnRpYy1jb3J0ZXg:7.2.0 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.

src/core/repl-executor.jsView on unpkg

scripts/generate-graph.mjsView file

•matchType = normalized_sha256 matchedPackage = agentic-cortex@7.2.0 matchedPath = scripts/generate-graph.mjs matchedIdentity = npm:YWdlbnRpYy1jb3J0ZXg:7.2.0 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.

scripts/generate-graph.mjsView on unpkg

src/bench/locomo.jsView file

•matchType = normalized_sha256 matchedPackage = agentic-cortex@7.2.0 matchedPath = src/bench/locomo.js matchedIdentity = npm:YWdlbnRpYy1jb3J0ZXg:7.2.0 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.

src/bench/locomo.jsView on unpkg

Source & flagged code

15 flagged · loading source

package.jsonView file

•scripts.postinstall = node scripts/auto-setup.js

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg

src/core/hooks.jsView file

185if (process.env.AGENTIC_CORTEX_HOOKS_JS !== '1') return false; L186: try { return new Function('obs', 'ctx', value)(observation, context); } catch { return false; } L187: default:

Low

Eval

Package source references a known benign dynamic code generation pattern.

src/core/hooks.jsView on unpkg · L185

scripts/create-discovery-files.jsView file

5Install-time code directly mutates a foreign AI-agent control surface: L5: * Creates files that various AI coding agents automatically read at session start: L6: * - AGENTS.md (OpenCode, Claude Code — canonical MCP-first discovery) L7: * - .claude/CLAUDE.md (Claude Code) L8: * - .cursor/rules/agentic-cortex.mdc (Cursor, alwaysApply: true) L9: * - .opencode/agentic-cortex.md (OpenCode / Codebuff) L10: * L11: * Also creates MCP server configuration files: L12: * - .mcp.json (Claude Code) L13: * - .cursor/mcp.json (Cursor) L14: * - opencode.json (OpenCode) L15: * ... L95: * Idempotent — skips if agentic-cortex already configured. Write operation from scripts/auto-setup.js: L89: if (fs.existsSync(templatePath)) { L90: fs.copyFileSync(templatePath, knowledgePa

Critical

Ai Agent Control Hijack

Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.

scripts/create-discovery-files.jsView on unpkg · L5

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.

scripts/create-discovery-files.jsView on unpkg

scripts/cortex-hook.shView file

•path = scripts/cortex-hook.sh kind = build_helper sizeBytes = 7908 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

scripts/cortex-hook.shView on unpkg

src/core/code-index.js#virtual:normalized:round1View file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 2

High

Semantic Analysis Limited

A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.

src/core/code-index.js#virtual:normalized:round1View on unpkg

cli.jsView file

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

cli.jsView on unpkg

scripts/import-community-knowledge.jsView file

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

scripts/import-community-knowledge.jsView on unpkg

scripts/seed-memory-repo.jsView file

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

scripts/seed-memory-repo.jsView on unpkg

src/core/failure-classifier.jsView file

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

src/core/failure-classifier.jsView on unpkg

scripts/auto-setup.jsView file

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

scripts/auto-setup.jsView on unpkg

scripts/inject-memory.mjsView file

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

scripts/inject-memory.mjsView on unpkg

src/core/repl-executor.jsView file

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

src/core/repl-executor.jsView on unpkg

scripts/generate-graph.mjsView file

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

scripts/generate-graph.mjsView on unpkg

src/bench/locomo.jsView file

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

src/bench/locomo.jsView on unpkg

Findings

1 Critical12 High4 Medium5 Low

CriticalAi Agent Control Hijackscripts/create-discovery-files.js

HighInstall Time Lifecycle Scriptspackage.json

HighTrigger Reachable External Ai Agent Control Surface Mutationscripts/create-discovery-files.js

HighSemantic Analysis Limitedsrc/core/code-index.js#virtual:normalized:round1

HighKnown Malware Source Similaritycli.js

HighKnown Malware Source Similarityscripts/import-community-knowledge.js

HighKnown Malware Source Similarityscripts/seed-memory-repo.js

HighKnown Malware Source Similaritysrc/core/failure-classifier.js

HighKnown Malware Source Similarityscripts/auto-setup.js

HighKnown Malware Source Similarityscripts/inject-memory.mjs

HighKnown Malware Source Similaritysrc/core/repl-executor.js

HighKnown Malware Source Similarityscripts/generate-graph.mjs

HighKnown Malware Source Similaritysrc/bench/locomo.js

MediumNetwork

MediumEnvironment Vars

MediumShips Build Helperscripts/cortex-hook.sh

MediumStructural Risk Force Deep Review

LowScripts Present

LowEvalsrc/core/hooks.js

LowFilesystem

LowHigh Entropy Strings

LowUrl Strings

Affected versions and remediation

This report applies to agentic-cortex@7.1.0.

See version security history for other recorded verdicts.

Review the evidence and your use of agentic-cortex@7.1.0 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: 2026-09-19 15:40:11.838Z (UTC).