registry / @qzhuli/qzhuli-cli / 0.5.10

@qzhuli/qzhuli-cli@0.5.10

CLI tool for Q助理 (QZhuli)

AI Security Review

scanned 1mo ago · by lpm-firewall-ai

LPM flags this version as an AI-agent control-surface risk. npm installation automatically installs and updates a bundled skill in foreign AI-agent control directories. It can create directories and delete stale files in those skill locations.

Static reason

High-risk behavior combination matched malicious policy.

Trigger

npm postinstall

Impact

Unconsented modification of broad global or project AI-agent control surfaces.

Mechanism

Automatic cross-agent skill installation and replacement

Policy narrative

Installing the package invokes postinstall without a user command. The script detects numerous AI-agent installations, defaults to Claude Code when none are found, always includes a generic agents directory, and copies its bundled skill there. Its copy routine removes destination entries that are no longer present in the package before writing the replacement content. This is an unconsented install-time mutation of foreign and broad AI-agent control surfaces.

AI rationale

The automatic lifecycle hook modifies multiple external AI-agent skill directories, including fallback targets, rather than limiting setup to an explicit user command or package-owned location. This meets the install-control-surface blocking policy.

Evidence

package.jsonscripts/postinstall.mjsscripts/skill-agent.mjsskills/qzhuli-cli~/.claude/skills/qzhuli-cli~/.codex/skills/qzhuli-cli~/.agents/skills/qzhuli-cli

@qzhuli/qzhuli-cli@0.5.10

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Affected versions and remediation

Source & flagged code