registry / AI-agent capability abuse / @caelo-cms/mcp-server / 0.10.41

@caelo-cms/mcp-server@0.10.41

MCP servers for Caelo CMS: `caelo_chat` (talk to Caelo's own AI) and the admin-scoped Power-MCP (the full chat-runner tool catalogue, driven by your own agent). Lets Claude Code (or any MCP-aware client) drive a Caelo install from outside the browser.

AI Security Review

scanned 10d ago · by lpm-firewall-ai

The package has no install-time lifecycle behavior, and the flagged credential flow uses configured admin and Google IAM endpoints. The explicit export command writes live context into Claude Code files, so the agent configuration capability warrants a warning.

Static reason

High-risk behavior combination matched malicious policy.; source fingerprint signature matched known malicious package; routed for review

Trigger

A user runs the package with the export command.

Impact

The generated files can affect Claude Code guidance in that directory. The source shows no automatic install-time write or update trigger.

Mechanism

The command retrieves live context from the configured admin install and writes CLAUDE.md plus skill files under .claude/skills.

AI rationale

Evidence

package.jsondist/index.jsdist/export.jsdist/http.jsdist/ingress-auth.jsCLAUDE.md.claude/skills/<slug>/SKILL.md

Network endpoints1

iamcredentials.googleapis.com

Decision evidence

public snapshot

AI called this Suspicious at 90.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

The manifest has only a prepublishOnly hook, which runs the build.
The export behavior is activated by the explicit export command and defaults to the current directory unless --out is supplied.
Export requests live context from the configured admin install using the supplied token.
Export writes generated context to CLAUDE.md and writes skill bodies to validated .claude/skills/<slug>/SKILL.md paths.
Normal API requests send the token to the configured admin URL; the IAP flow uses Google IAM to sign a JWT for that admin origin.
The admin binary reads the admin URL and token from environment variables before starting its server.

Evidence against

Behavioral surface

Source

EnvironmentVarsFilesystemNetwork

Supply chain

HighEntropyStringsUrlStrings

Manifest

CopyleftLicense

scanned 10 file(s), 47.6 KB of source, external domains: admin.example.com, iamcredentials.googleapis.com, www.googleapis.com

Source & flagged code

3 flagged

dist/ingress-auth.jsView file

Lines 8-48javascript

8 * runs, so the shim has to satisfy both gates: IAP first, Caelo second

9 * (CLAUDE.md §11.B — IAP stays the first line of defense).

10 *

11 * Cloud Run native IAP uses a Google-managed OAuth client, which does not

12 * allow programmatic access with user tokens. What it does accept is a

13 * JWT signed by an allowlisted service account (Google's documented

14 * "service account JWT" path): `iss`/`sub` = the SA, `aud` = the admin

15 * origin with a path wildcard, signed via the IAM Credentials `signJwt`

16 * API. The provisioner creates that SA (`caelo-mcp@<project>`), allowlists

17 * it on IAP and lets every IAP-allowlisted operator impersonate it, so the

18 * operator's own `gcloud auth application-default login` is all the shim

19 * needs — no service-account keys on laptops (CLAUDE.md §11.C).

20 *

21 * Active only when `CAELO_IAP_SERVICE_ACCOUNT` is set (the admin's

22 * /security/mcp page puts it into the `claude mcp add` command on IAP

23 * installs); otherwise requests go out exactly as before.

24 */

25import { GoogleAuth } from "google-auth-library";

26/** Signed JWTs live at most 1 hour; refresh a minute before expiry. */

27const TOKEN_LIFETIME_S = 3600;

28const REFRESH_MARGIN_S = 60;

29/** `https://admin.example.com/anything` → `https://admin.example.com/*` (the JWT `aud`). */

30export function iapAudience(adminUrl) {

Critical

Hardcoded Runtime Data Exfiltration

Source sends credentials or rich application records to a package-controlled external receiver enabled by default.

dist/ingress-auth.jsView on unpkg · L28

Critical

Trigger Reachable Dangerous Capability

A package entrypoint or install-time lifecycle script reaches a source file with blocking dangerous behavior.

dist/ingress-auth.jsView on unpkg · L28

31 return `${new URL(adminUrl).origin}/*`;

32}

33async function adcAccessToken() {

34 const auth = new GoogleAuth({ scopes: ["https://www.googleapis.com/auth/cloud-platform"] });

35 const token = await auth.getAccessToken();

36 if (!token)

37 throw new Error("Application Default Credentials returned no access token");

38 return token;

39}

40export function createIngressAuth(env, deps = {}) {

41 const configured = env.CAELO_IAP_SERVICE_ACCOUNT?.trim();

42 if (!configured)

43 return null;

44 const serviceAccount = configured;

45 if (!env.CAELO_ADMIN_URL)

46 throw new Error("CAELO_IAP_SERVICE_ACCOUNT is set but CAELO_ADMIN_URL is not");

47 const audience = iapAudience(env.CAELO_ADMIN_URL);

48 const getAccessToken = deps.getAccessToken ?? adcAccessToken;

dist/admin.jsView file

•matchType = malicious_source_fingerprint_signature signature = 9c62746250c2b8fc signatureType = suspicious_hashes sourceLabel = final_verdict:malicious matchedPackage = @caelo-cms/mcp-server@0.10.40 matchedPath = dist/admin.js matchedIdentity = npm:QGNhZWxvLWNtcy9tY3Atc2VydmVy:0.10.40 similarity = 1.000 shingleOverlap = 9 summary = package final verdict is malicious

High

Known Malware Source Fingerprint Signature

Source fingerprint signature matches a known malicious package signature; route for source-aware review.

dist/admin.jsView on unpkg

Source & flagged code

3 flagged · loading source

dist/ingress-auth.jsView file

28const REFRESH_MARGIN_S = 60; L29: /** `https://admin.example.com/anything` → `https://admin.example.com/*` (the JWT `aud`). */ L30: export function iapAudience(adminUrl) { ... L66: headers: { authorization: `Bearer ${accessToken}`, "content-type": "application/json" }, L67: body: JSON.stringify({ L68: payload: JSON.stringify({ ... L77: if (!res.ok) { L78: const detail = await res.text().catch(() => ""); L79: throw new Error(`IAP: could not sign an access token as ${serviceAccount} (HTTP ${res.status}). ` + ... L103: let processIngress; L104: /** Ingress headers for this process, configured from `process.env` on first use. */ L105: export async function ingressHeaders() {

Critical

Hardcoded Runtime Data Exfiltration

Source sends credentials or rich application records to a package-controlled external receiver enabled by default.

dist/ingress-auth.jsView on unpkg · L28

28Trigger-reachable chain: manifest.main -> dist/index.js -> dist/admin-server.js -> dist/http.js -> dist/ingress-auth.js L28: const REFRESH_MARGIN_S = 60; L29: /** `https://admin.example.com/anything` → `https://admin.example.com/*` (the JWT `aud`). */ L30: export function iapAudience(adminUrl) { ... L66: headers: { authorization: `Bearer ${accessToken}`, "content-type": "application/json" }, L67: body: JSON.stringify({ L68: payload: JSON.stringify({ ... L77: if (!res.ok) { L78: const detail = await res.text().catch(() => ""); L79: throw new Error(`IAP: could not sign an access token as ${serviceAccount} (HTTP ${res.status}). ` + ... L103: let processIngress; L104: /** Ingress headers for this process, configured from `process.env` on first use. */ L105: export async function ingressHeaders

Findings

2 Critical1 High3 Medium6 Low

CriticalHardcoded Runtime Data Exfiltrationdist/ingress-auth.js

CriticalTrigger Reachable Dangerous Capabilitydist/ingress-auth.js

HighKnown Malware Source Fingerprint Signaturedist/admin.js

MediumNetwork

MediumEnvironment Vars

MediumStructural Risk Force Deep Review

LowNon Install Lifecycle Scripts

LowScripts Present

LowFilesystem

LowHigh Entropy Strings

LowUrl Strings

LowCopyleft License

Affected versions and remediation

This report applies to @caelo-cms/mcp-server@0.10.41.

See all versions of @caelo-cms/mcp-server for other recorded verdicts.

Review the evidence and your use of @caelo-cms/mcp-server@0.10.41 before allowing it. Restrict the permissions described in this report.
Choose an independently verified alternative or release. This report does not establish that other versions are safe.

Evidence last updated: 2026-10-13 09:18:29.482Z (UTC).

Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.