registry / agentic-cortex / 3.3.0

agentic-cortex@3.3.0

Persistent typed memory for AI coding agents — install & forget: auto-inject context via git hooks, 13 memory types, confidence tracking, conflict detection, grounded QA, codebase graphs

AI Security Review

scanned 1mo ago · by lpm-firewall-ai

No confirmed malicious attack surface is established. The package is a user-invoked AI memory CLI/MCP server that stores SQLite data, can generate/inject local context, and can optionally install git hooks for auto-refresh.

Static reason

No blocking static signals were detected.; previous stored version diff introduced dangerous source

Trigger

User runs CLI commands such as setup, hook install, graph, inject, MCP tools, or imports and calls the API

Impact

Local project files may be read for graphing and knowledge.md/.git/hooks may be written when explicit commands are used; no unconsented install-time behavior or exfiltration found

Mechanism

local memory database, code graph generation, optional context injection and git hook installation

Rationale

Static inspection found potentially sensitive local automation primitives, but they are explicit package features activated by user commands and no lifecycle execution, credential theft, external exfiltration, or covert persistence was found. The scanner's dangerous-delta hint maps to a code graph generator that reads local source and writes a cache for documented context injection.

Evidence

package.jsoncli.jsscripts/inject-memory.mjsscripts/generate-graph.mjssrc/api/index.jssrc/core/hooks.jssrc/core/session.jssrc/mcp/server.jsknowledge.md.git/hooks/post-merge.git/hooks/post-checkout.git/hooks/post-rewrite.infinit-graph.json

agentic-cortex@3.3.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code