Audit

Two supply chains, not one.

The packages you import are audited by everyone. The programs your agent launches are audited by almost no one.

Download for macOS
v0.1.33 · .dmg · Apple Silicon & Intel
Signed & notarized by Apple · opens without a Gatekeeper warning
sha256 698955a0187bc039f4c74f5d05a9f10fbb27376a45788a0a241d1326b73873c7
Download for Windows instead
$curl -fsSL https://lucidtrain.com/install.sh | sh

Dependency scanning covers the packages your code imports. It says nothing about the second supply chain that arrived with agentic development: the MCP servers, launched by your agent with your agent's permissions, frequently via an unpinned fetch that resolves fresh on every start. Lucid Train audits both. The dependency half uses installed scanners over your manifests; the agent half parses your MCP configuration for unpinned launches, remote endpoints, plaintext transport and credentials being passed through.

The second supply chain is new and unguarded

Package managers grew lockfiles, signatures and advisory databases over two decades. Agent tooling arrived in about two years, and the common installation instruction is a command that fetches the latest version at every launch. The threat model is familiar and the controls have not caught up, which is the entire reason the agent-config half of this audit exists.

Why the same tab covers both

They are the same question asked about two inventories: what runs here, where did it come from, and could it change under you. Reporting them together means the answer is one report rather than a dependency scan and a gap where nothing looks at the agent configuration at all.

What it is and what it is not

Worth being exact about the boundary, because the category name is crowded. This reads dependency manifests and lockfiles, not your source code. It will tell you that a package you depend on has a known vulnerability. It will not find an injection flaw, a broken authorisation check or a hardcoded credential in a file you wrote, because it never opens those files. For that you want a static analysis tool, and the two are complements rather than substitutes.

Findings you can act on immediately

Both halves produce concrete, checkable actions: pin this package to a version, vendor this server, narrow this credential, upgrade this dependency to the version that carries the fix. The agent is in the same window with the repository open, so acting on one is an edit you review rather than a task you file.

Two inventories, one report

DependenciesAgent tooling
What it coversPackages you importMCP servers your agent launches
Source of truthManifests and lockfilesAgent config JSON
Needs a scanner installedYesNo
Needs the networkDepends on the scannerNo
Typical findingKnown advisory in a packageUnpinned launch or remote endpoint
FAQ

Questions

What is the second supply chain?

The programs your coding agent is configured to launch, chiefly MCP servers. They run with the agent's file and network access and are often fetched unpinned at every start.

Does it produce an SBOM?

No. It inventories manifests to drive scanning, but there is no SBOM export and no license or provenance analysis.

Is the agent-config half useful without any scanners installed?

Yes, and it is the part that always works. It needs no external tool and no network, so it runs on any machine and in any repository.

Related

Last updated