@respira/wordpress-mcp-server@8.4.16
WordPress MCP server + companion plugin giving AI native access to page builder content, not just the REST API. 248 tools, 352 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-aiThe source supports a warning for explicit agent configuration and skill installation capabilities, while showing their command-based triggers and setup token gate. No package install hook or concrete malicious behavior was found.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
A user runs the setup executable with --install-config, a supported --client value, and an install token; a user may also run the separate skill installer.
Impact
Running setup can change which MCP server configuration an agent loads, while installing skills adds package-provided instructions to the user's skill directory; source inspection found no evidence of secret theft or stealth activation.
Mechanism
Setup fetches a token-associated configuration from the configured Respira website and merges its named server entry into the selected client config. The skills command copies bundled Respira skill files to its selected destination.
AI rationale
The source supports a warning for explicit agent configuration and skill installation capabilities, while showing their command-based triggers and setup token gate. No package install hook or concrete malicious behavior was found.
Evidence
~/.cursor/mcp.json~/.codex/config.toml~/.claude.json~/.antigravity/mcp.json~/.hermes/config.yaml~/.claude/skills
Network endpoints1
www.respira.press
Decision evidence
public snapshotAI called this Suspicious at 90.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The package exposes setup and skill installation as explicit command entry points; package.json declares no install lifecycle hook.
- Setup writes a Respira server entry into a selected agent configuration only when invoked with --install-config and a client plus install token.
- The setup command fetches the config from the Respira website and merges the named server entry into the existing agent config.
- The skills command copies bundled Respira skills to ~/.claude/skills by default, and supports an explicit destination; existing skills are skipped unless --force is used.
- The config target code identifies agent configuration paths, while ordinary server output cleanup redacts known secrets.
- The server process scan is bounded to identifying sibling Respira MCP processes.
Evidence against
- The inspected setup mutation is reached through an explicit CLI flag and requires an install token; it is not an npm install hook.
- The setup merge targets the selected Respira server entry, and Hermes configuration is left untouched when a nonempty file exists.
- No concrete credential exfiltration, stealth persistence, destructive behavior, or active attack was identified.
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 = 3
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
MediumAi Review Evidencedist/setup.js
MediumAi Review Evidencedist/setup.js
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @respira/wordpress-mcp-server@8.4.16.
See all versions of @respira/wordpress-mcp-server for other recorded verdicts.
- Review the evidence and your use of @respira/wordpress-mcp-server@8.4.16 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.