Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward X/Twitter search helper that sends user search queries to xAI using the user's API key.
Install only if you are comfortable sending search text, handles, date filters, and media options to xAI/X services under your XAI_API_KEY. Avoid putting secrets, private business information, or personal data in search queries, and be aware the API key may incur provider usage costs.
The skill declares code-relevant capabilities via required environment variables and an external API workflow, but it does not explicitly declare a permission or allowed-tools scope. That creates an authorization ambiguity: an agent/runtime may grant broader network or environment access than reviewers expect, making secret handling and outbound requests less constrained and less auditable.
The invocation guidance says to use the skill when the user wants to "find tweets," "search X/Twitter," "look up what people are saying on X," or "find social media posts about a topic." These are broad natural-language cues without exclusion conditions or clearer scope boundaries, which could cause the skill to activate for ordinary conversational requests that mention social media research.
The skill description contains broad trigger phrases like 'find tweets', 'search X/Twitter', and 'look up what people are saying on X', which can match many ordinary user requests and cause the skill to be invoked more often than necessary. Because the skill sends user queries to an external API, over-broad routing increases the chance that unrelated or sensitive user prompts are transmitted off-platform without clear user intent.
The usage section instructs users to run searches against the xAI API but does not warn that search terms will be transmitted to an external third-party service. This can lead users to include sensitive, proprietary, or personal information in queries without informed consent, creating a privacy and data handling risk.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
def redirect_request(self, req, fp, code, msg, headers, newurl):
raise HTTPError(newurl, code, f"Redirect to {newurl} blocked (auth safety)", headers, fp)
API_URL = "https://api.x.ai/v1/responses"
MODEL = "grok-4.20-reasoning"
TIMEOUT_S = 120
MAX_HANDLES = 10
This code collects the user's query and optional X handle/date filters, then transmits them in an HTTP POST request to the xAI API. While the module docstring says it uses the Grok API, there is no user-facing print/log/prompt at execution time warning that user-provided search content will be sent to an external service.
The code requires and reads XAI_API_KEY from the environment before performing the search. While credential use may be common for an API-backed integration, the manifest description does not mention handling secrets or environment access, so this is an extra capability not directly stated in the skill purpose.
No suspicious patterns detected.