registry / AI-agent capability abuse / @respira/wordpress-mcp-server / 8.4.3

@respira/wordpress-mcp-server@8.4.3

WordPress MCP server + companion plugin giving AI native access to page builder content, not just the REST API. 242 tools, 346 with WooCommerce, 17 page builders and the Site Editor. Element-level edits, full page creation, HTML to builder conversion, sna

AI Security Review

scanned 12d ago · by lpm-firewall-ai

The setup and skills integration commands mutate agent configuration or skill directories when explicitly invoked, so the integration remains a warning-level capability. Inspected sources do not show a concrete attack or install-time execution.

Static reason

No blocking static signals were detected.; previous stored version diff introduced dangerous source

Trigger

A user runs the setup executable with the install-config option and supplies a supported client and install token.

Impact

The agent's configuration is changed to include the Respira server; no unconsented install-time mutation or credential theft was identified.

Mechanism

The command fetches token-authorized Respira configuration and merges its server entry into the selected client's configuration file.

AI rationale

Evidence

dist/setup.js

Network endpoints1

www.respira.press

Decision evidence

public snapshot

AI called this Suspicious at 84.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

The package exposes setup and skills installers as executable commands, with no npm lifecycle hook in the manifest.
The setup command accepts an explicit install-config flag and requires a supported client and install token.
Setup fetches a server configuration using that token and merges its server entry into a selected agent configuration file.
The skills command defaults to the user's Claude skills directory and copies bundled skill files there when invoked.
Config resolution warns when a config file shadows environment credentials; it does not itself send those credentials elsewhere.
The server process listing is used to identify sibling processes.

Evidence against

The agent configuration and skills changes are user-invoked; the inspected sources do not show them running from npm install hooks.

Behavioral surface

Source

ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell

Supply chain

Source & flagged code

6 flagged

dist/install-skills.jsView file

Lines 14-54javascript

14 * scripts/bundle-skills.mjs copies plugins/respira-wordpress/skills/ into

15 * skills/ before tsc runs, and the same folder backs the MCP prompts the

16 * server offers (skill-prompts.ts).

17 */

18import * as fs from 'fs';

19import * as path from 'path';

20import * as os from 'os';

21import { fileURLToPath } from 'url';

22const __filename = fileURLToPath(import.meta.url);

23const __dirname = path.dirname(__filename);

24// Resolve the bundled skills directory relative to the compiled JS.

25// dist/install-skills.js -> ../skills (sibling to dist/ inside the package)

26const BUNDLED_SKILLS_DIR = path.resolve(__dirname, '..', 'skills');

27const c = {

28 reset: '\x1b[0m',

29 bold: '\x1b[1m',

30 dim: '\x1b[2m',

31 red: '\x1b[31m',

32 green: '\x1b[32m',

33 yellow: '\x1b[33m',

34 blue: '\x1b[34m',

35 cyan: '\x1b[36m',

36};

37function parseArgs(argv) {

38 const opts = {

39 dest: path.join(os.homedir(), '.claude', 'skills'),

40 force: false,

41 help: false,

Medium

Ai Review Evidence

The skills command defaults to the user's Claude skills directory and copies bundled skill files there when invoked.

dist/install-skills.jsView on unpkg · L34

42 };

43 for (let i = 0; i < argv.length; i++) {

44 const arg = argv[i];

45 if (arg === '--help' || arg === '-h') {

46 opts.help = true;

47 }

48 else if (arg === '--force' || arg === '-f') {

49 opts.force = true;

50 }

51 else if (arg === '--dest' || arg === '-d') {

52 const next = argv[i + 1];

53 if (!next || next.startsWith('-')) {

54 console.error(`${c.red}error:${c.reset} --dest requires a path argument`);

•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation. const bundled_skills_dir = path.resolve(__dirname, '..', 'skills'); const c = { reset: '\x1b[0m', bold: '\x1b[1m', dim: '\x1b[2m', red: '\x1b[31m', green: '\x1b[32m', yellow: '\x1b[33m', blue: '\x1b[34m', cyan: '\x1b[36m', }; function parseargs(argv) { const opts = { dest: path.join(os.homedir(), '.claude', 'skills'), force: false, help: false, }; for (let i = 0; i < argv.length; i++) { const arg = argv[i]; if (arg === '--help' || arg === '-h') { opts.help = true; } else if (arg === '--force' || arg === '-f') { opts.force = true; } else if (

High

Trigger Reachable External Ai Agent Control Surface Mutation

Manifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.

dist/install-skills.jsView on unpkg

dist/config.js#virtual:normalized:round1View file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 2

High

Semantic Analysis Limited

A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.

dist/config.js#virtual:normalized:round1View on unpkg

dist/server.jsView file

•matchType = previous_version_dangerous_delta matchedPackage = @respira/wordpress-mcp-server@8.3.24 matchedIdentity = npm:[redacted]:8.3.24 similarity = 0.875 summary = stored previous version shares package body but lacks this dangerous source file

High

Previous Version Dangerous Delta

This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.

dist/server.jsView on unpkg

package.jsonView file

Lines 1-26json

2 "name": "@respira/wordpress-mcp-server",

3 "version": "8.4.3",

4 "mcpName": "io.github.webmyc/respira-wordpress",

5 "description": "WordPress MCP server + companion plugin giving AI native access to page builder content, not just the REST API. 242 tools, 346 with WooCommerce, 17 page builders and the Site Editor. Element-level edits, full page creation, HTML to builder conversion, snapshots and rollback on every write. MCP 2026-07-28 with legacy-client support. New in 8.3: Design Direction, one design system per site, applied to native builder stores, checked against the rendered page, with a live preview link for the Art Direction dashboard."

dist/config.jsView file

Lines 624-664javascript

624 console.warn(`Warning: ${explicitPath} does not exist${rawExplicitPath !== explicitPath ? ` (RESPIRA_CONFIG_FILE was ${rawExplicitPath})` : ''}. Server is starting in bootstrap mode; only respira_redeem_token will work until the user redeems a token from respira.press/dashboard/mcp.`);

625 }

626

Source & flagged code

6 flagged · loading source

dist/install-skills.jsView file

High

Trigger Reachable External Ai Agent Control Surface Mutation

Manifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.

dist/install-skills.jsView on unpkg

34\x1b[34m', cyan: '\x1b[36m', }; function parseArgs(argv) { const opts = { dest: path.join(os.homedir(), '.claude', 'skills'), force: false, help: fa

Medium

Ai Review Evidence

The skills command defaults to the user's Claude skills directory and copies bundled skill files there when invoked.

dist/install-skills.jsView on unpkg · L34

Findings

3 High5 Medium4 Low

HighTrigger Reachable External Ai Agent Control Surface Mutationdist/install-skills.js

HighSemantic Analysis Limiteddist/config.js#virtual:normalized:round1

HighPrevious Version Dangerous Deltadist/server.js

MediumNetwork

MediumEnvironment Vars

MediumSuspicious Lifecycle Evidencepackage.json

MediumAi Review Evidencedist/config.js

MediumAi Review Evidencedist/install-skills.js

LowScripts Present

LowFilesystem

LowHigh Entropy Strings

LowUrl Strings

Affected versions and remediation

This report applies to @respira/wordpress-mcp-server@8.4.3.

See all versions of @respira/wordpress-mcp-server for other recorded verdicts.

Review the evidence and your use of @respira/wordpress-mcp-server@8.4.3 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: 2026-10-11 04:17:09.674Z (UTC).

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

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Affected versions and remediation

Runtime surface

Behavioral surface

Source & flagged code