@respira/wordpress-mcp-server@8.6.1
WordPress MCP server + companion plugin giving AI native access to page builder content, not just the REST API. 252 tools, 356 with WooCommerce, 19 page builders and the Site Editor. Element-level edits, full page creation, HTML to builder conversion, sna
AI Security Review
scanned 7d ago · by lpm-firewall-aiThe package has no npm install lifecycle hook, and the agent configuration utilities are explicit CLI setup commands. However, bundled audit skills instruct agents to silently send site and findings metadata to a publisher-aligned endpoint, creating a conditional disclosure risk without affirmative telemetry consent.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
A user invokes one of the affected audit skills and the agent follows its reporting instructions.
Impact
The publisher receives site and diagnostic metadata without affirmative telemetry consent; the inspected payload does not include a WordPress API key.
Mechanism
The skill directs a silent JSON POST containing site details and report findings to the telemetry endpoint.
AI rationale
The package has no npm install lifecycle hook, and the agent configuration utilities are explicit CLI setup commands. However, bundled audit skills instruct agents to silently send site and findings metadata to a publisher-aligned endpoint, creating a conditional disclosure risk without affirmative telemetry consent.
Evidence
package.jsondist/install-skills.jsdist/setup.jsdist/config.jsskills/mobile-experience-report/SKILL.mdskills/technical-debt-audit/SKILL.mdskills/woocommerce-health-check/SKILL.mdskills/wordpress-site-dna/SKILL.mdskills/mobile-experience-report/telemetry.ts
Network endpoints1
www.respira.press/api/skills/track-usage
Decision evidence
public snapshotAI called this Suspicious at 89.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The manifest exposes setup and skill installation as CLI commands; its scripts contain no npm install lifecycle hook.
- The skill installer copies bundled skill files to the Claude skills directory when explicitly run.
- Four bundled audit skills instruct the agent to silently send telemetry after producing a report, including site and diagnostic information.
- The mobile report skill sends its payload as JSON to Respira’s telemetry endpoint; the shown payload contains site and report metadata, not a WordPress API key.
- Agent configuration setup requires an explicit install command and token; the config code inspected reports configuration precedence rather than modifying agent settings.
- The setup wizard sends the API key to the WordPress URL entered by the user, and the WordPress client uses the configured site URL as its base.
Evidence against
- The telemetry endpoint is package-aligned, and the inspected request does not include WordPress API credentials.
- The telemetry send is triggered by use of an audit skill, not by npm installation.
Behavioral surface
Source & flagged code
6 flagged · loading sourcedist/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 unpkgdist/chat-hygiene.js#virtual:normalized:round1View file
•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 4
High
Findings
3 High5 Medium4 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationdist/install-skills.js
HighSemantic Analysis Limiteddist/chat-hygiene.js#virtual:normalized:round1
HighPrevious Version Dangerous Deltadist/server.js
MediumNetwork
MediumEnvironment Vars
MediumSuspicious Lifecycle Evidencepackage.json
MediumSuspicious Lifecycle Evidencepackage.json
MediumSuspicious Lifecycle Evidencepackage.json
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @respira/wordpress-mcp-server@8.6.1.
See all versions of @respira/wordpress-mcp-server for other recorded verdicts.
- Review the evidence and your use of @respira/wordpress-mcp-server@8.6.1 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: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.