Codex CLI plugin that turns a request into a goal with checks, keeps the evidence in your project and hands unfinished work to the next session.
Allowed — no malicious behavior detected
19 low-signal patterns reviewed and cleared.
AI security review
scanned · by lpm-firewall-ai
Source inspection resolved the high-risk hints to a gated package-cache prewarm, a read-only Codex plugin probe, and benign document, test, and DOM-analysis artifacts. The package’s agent setup is exposed through its explicit install command; no concrete attack behavior was found.
The postinstall helper proceeds only on a global install when CI is unset.
Impact
No credential exposure, unrelated account action, consumer policy change, or unconsented foreign agent-control mutation was identified.
Mechanism
It invokes the motion runtime to prepare pinned dependencies with install scripts disabled.
Decision evidence
public snapshot
Evidence for AI clean decision
The manifest’s postinstall runs a helper that exits unless this is a global install outside CI.
The motion prewarm uses a package cache and pinned lockfile, and disables dependency install scripts.
The flagged Codex module probes the plugin list; its declaration exposes a boolean probe result.
The installer presents agent and config destinations under the Codex home, and the CLI dispatches setup through its install command.
The flagged ancillary paths contain a Word document XML member, mocked figure-export tests, and a DOM findings function.
Evidence against
Behavioral surface
SourceChild process · Crypto · Dynamic require · Environment variables · Filesystem · Network · Shell · Web socket
Supply chainHigh entropy strings · URL strings
ManifestNo manifest risk signals triggered.
Scanned 322 files · 2.51 MB of source
11 external domains referenced
127.0.0.1
api.typesafe.ai
biomejs.dev
clangd.llvm.org
doi.org
github.com
lit.stage
raw.githubusercontent.com
registry.npmjs.org
www.apache.org
www.w3.org
Findings
2 critical · 4 high · 7 medium · 6 low
Automated scan signals; the review checked them and cleared this version. Where they are, most severe file first. Code opens a file's flagged lines, with their evidence, below.