Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward xAI Grok web/X search connector, but users should understand that their search queries are sent to xAI.
Install only if you are comfortable sending web/X search queries, filters, and optional media-understanding requests to xAI's API. Avoid confidential, regulated, or sensitive internal searches unless your xAI account and data-handling terms allow it, and keep the XAI_API_KEY protected.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
homepage: https://github.com/yourusername/xai-grok-search
metadata:
category: search
api_base: https://api.x.ai/v1
capabilities:
- api
- web-search
The skill is explicitly designed to send user-provided queries to xAI's external API, but the user-facing guidance does not clearly warn that prompts, search terms, and potentially attached media will be transmitted to a third party. This creates a real privacy and data-handling risk, especially if users assume the query stays local or do not realize X/web searches may include sensitive terms.
The URL match here corresponds to the actual outbound request path used by the web search implementation, so it is a real external transmission sink rather than a purely descriptive reference. In context, the skill is a search connector, which makes the behavior expected, but it still poses privacy risk if sensitive prompts are forwarded without clear disclosure.
if (excluded_domains) tool.excluded_domains = excluded_domains;
if (enable_image_understanding) tool.enable_image_understanding = true;
const response = await fetch('https://api.x.ai/v1/responses', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
The URL match here corresponds to the actual outbound request path used by the web search implementation, so it is a real external transmission sink rather than a purely descriptive reference. In context, the skill is a search connector, which makes the behavior expected, but it still poses privacy risk if sensitive prompts are forwarded without clear disclosure.
if (excluded_domains) tool.excluded_domains = excluded_domains;
if (enable_image_understanding) tool.enable_image_understanding = true;
const response = await fetch('https://api.x.ai/v1/responses', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
The URL match here is tied to the X search implementation's outbound request and therefore represents a true data egress point. Because this path can also enable media understanding, the context makes accidental disclosure more severe than a simple text-only lookup.
if (enable_image_understanding) tool.enable_image_understanding = true;
if (enable_video_understanding) tool.enable_video_understanding = true;
const response = await fetch('https://api.x.ai/v1/responses', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
The URL match here is tied to the X search implementation's outbound request and therefore represents a true data egress point. Because this path can also enable media understanding, the context makes accidental disclosure more severe than a simple text-only lookup.
if (enable_image_understanding) tool.enable_image_understanding = true;
if (enable_video_understanding) tool.enable_video_understanding = true;
const response = await fetch('https://api.x.ai/v1/responses', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
This code performs an outbound HTTPS request to xAI's API containing user-controlled query content and tool configuration. External transmission is inherent to the skill's purpose, but it remains security-relevant because it can exfiltrate sensitive user input, and the function returns the full raw upstream response, increasing downstream exposure of third-party data.
if (enable_image_understanding) tool.enable_image_understanding = true;
// Make API request
const response = await fetch('https://api.x.ai/v1/responses', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
This code performs an outbound HTTPS request to xAI's API containing user-controlled query content and tool configuration. External transmission is inherent to the skill's purpose, but it remains security-relevant because it can exfiltrate sensitive user input, and the function returns the full raw upstream response, increasing downstream exposure of third-party data.
if (enable_image_understanding) tool.enable_image_understanding = true;
// Make API request
const response = await fetch('https://api.x.ai/v1/responses', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
The function sends the user-provided web search query and optional filters to xAI's external API, but the executable path provides no disclosure, consent prompt, or privacy notice before transmission. In a search skill this is expected behavior, but it is still a real privacy/security issue because users may unknowingly send sensitive prompts or internal data to a third party.
This function sends X search requests to an external service over the network with user-supplied content and filters. The behavior is expected for a search integration, but it still creates a real confidentiality and data-governance risk if callers assume searches are local or if sensitive topics are submitted.
if (enable_video_understanding) tool.enable_video_understanding = true;
// Make API request
const response = await fetch('https://api.x.ai/v1/responses', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
This function sends X search requests to an external service over the network with user-supplied content and filters. The behavior is expected for a search integration, but it still creates a real confidentiality and data-governance risk if callers assume searches are local or if sensitive topics are submitted.
if (enable_video_understanding) tool.enable_video_understanding = true;
// Make API request
const response = await fetch('https://api.x.ai/v1/responses', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
The X search path transmits the user's query and optional search constraints to xAI's external API without any warning in the executable path. Because X searches may include sensitive investigative, corporate, or personal topics, silent third-party transmission creates a meaningful confidentiality risk even if the feature is intended.
Detected: suspicious.env_credential_access