registry / memory-store-skill / 1.0.3

memory-store-skill@1.0.3

Conversation memory skill for multi-agent AI workflows — store, share, and recall across sessions and agents

AI Security Review

scanned 6d ago · by lpm-firewall-ai

LPM flags this version as an AI-agent control-surface risk. npm postinstall automatically scans for installed AI-agent platforms and installs package-controlled skill files into all detected agent skill directories. The installed SKILL.md imposes mandatory agent behavior.

Static reason

One or more suspicious static signals were detected.

Trigger

npm installation of memory-store-skill

Impact

Unconsented modification of multiple AI-agent control surfaces and persistent instruction injection.

Mechanism

postinstall-driven broad AI-agent skill deployment

Policy narrative

Installing the package triggers postinstall, which launches install.js with --all without user confirmation. That script detects nine vendor-specific AI-agent configuration locations, creates each detected skill directory, and copies SKILL.md plus package scripts there. SKILL.md then supplies mandatory behavioral instructions to those agents. This is an unconsented, broad modification of foreign AI-agent control surfaces.

Rationale

The package has a concrete automatic postinstall chain that installs its agent instructions into every detected supported platform. Local-only CLI behavior does not mitigate that unconsented control-surface mutation.

Evidence

package.jsonscripts/postinstall.jsscripts/install.jsSKILL.mdscripts/memory_cli.js~/.claude/skills/memory-store~/.agents/skills/memory-store~/.gemini/skills/memory-store~/.config/opencode/skills/memory-store~/.workbuddy/skills/memory-store

memory-store-skill@1.0.3

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code