registry / AI-agent capability abuse / @respira/wordpress-mcp-server / 8.3.17

@respira/wordpress-mcp-server@8.3.17

WordPress MCP server + companion plugin giving AI native access to page builder content, not just the REST API. 220 tools, 325 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 inspected agent configuration changes are available through explicit setup commands, and package.json contains no lifecycle hooks. This is a guarded agent setup capability, not evidence of an unconsented install-time attack.

Static reason

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

Trigger

The user runs the setup wizard or the install-skills command.

Impact

These commands change agent configuration or add skills, but the inspected code indicates user-invoked setup rather than an npm install hook.

Mechanism

Setup fetches configuration from the Respira service and writes or merges it into the selected agent configuration; install-skills copies bundled skill files to its configured destination.

AI rationale

Evidence

dist/setup.jsdist/install-skills.js

Network endpoints1

RESPIRA_WEBSITE_URL/api/mcp/config/export-by-token

Decision evidence

public snapshot

AI called this Suspicious at 89.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

The package has no npm lifecycle hooks; setup and skill installation are exposed as explicit commands in package.json.
The setup wizard can fetch Respira configuration and write it into supported agent configuration files when invoked with --setup.
The skill installer defaults to the user’s Claude skills directory and copies bundled skill files there when invoked.
The config.js target location is explanatory comment text about configuration precedence; it does not itself write agent configuration.
The main server entry imports MCP server libraries; no attack behavior was established from this excerpt.

Evidence against

Behavioral surface

Source

ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell

Supply chain

HighEntropyStringsPossibleObfuscationUrlStrings

ManifestNo manifest risk signals triggered.

Source & flagged code

6 flagged

dist/install-skills.jsView file

•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

40'.claude', 'skills'), force: false, help: false, }; for (let i = 0; i < argv.length; i++) { const arg = argv[i]; if (arg === '--help' || arg

Medium

Ai Review Evidence

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

dist/install-skills.jsView on unpkg · L40

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 = 0.864 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

2"name": "@respira/wordpress-mcp-server", "version": "8.3.17", "mcpName": "io.github.webmyc/respira-wordpress", "description": "WordPress MCP server + co

Medium

Suspicious Lifecycle Evidence

The package has no npm lifecycle hooks; setup and skill installation are exposed as explicit commands in package.json.

package.jsonView on unpkg · L2

dist/config.jsView file

721`.mcp.json`, or a RESPIRA_CONFIG_B64 pasted into the * client entry, silently outranks the file the operator just edited, and * nothing said so. * * That is 703 respira_site_id

Medium

Ai Review Evidence

The config.js target location is explanatory comment text about configuration precedence; it does not itself write agent configuration.

dist/config.jsView on unpkg · L721

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

40'.claude', 'skills'), force: false, help: false, }; for (let i = 0; i < argv.length; i++) { const arg = argv[i]; if (arg === '--help' || arg

Medium

Ai Review Evidence

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

dist/install-skills.jsView on unpkg · L40

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@8.3.17.

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

Review the evidence and your use of @respira/wordpress-mcp-server@8.3.17 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 04:13:05.390Z (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