Security audit
Security checks for vulnerabilities and agentic risk
This skill does what it says: it sends user search queries to xAI to search X/Twitter posts, with no hidden persistence or unrelated local access found.
Install only if you are comfortable sending search queries, handles, date filters, and your xAI API-authenticated request to xAI. Avoid using confidential project names, secrets, or personal data in searches unless that disclosure is acceptable for your xAI account and policies.
The skill invokes Python, reads environment variables, and makes outbound requests to the xAI API, but it does not declare any explicit tool scope such as permissions or allowed-tools. That creates a trust and review gap: the runtime capabilities are broader than what a user or platform policy can easily inspect up front, increasing the chance of unintended secret access or network use.
The description uses broad trigger phrases like 'find tweets,' 'look up what people are saying,' and 'find social media posts about a topic,' which can match many ordinary requests. Overbroad invocation criteria can cause the skill to run when the user did not specifically intend to send a query to X/xAI, leading to unnecessary external data sharing or surprising behavior.
The setup and usage text explains how to run searches but does not clearly warn that user queries are transmitted to the external xAI API for processing. If users or calling agents include sensitive terms, internal project names, or personal data in queries, that information may be disclosed to a third party without informed consent.
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
The manifest describes a user-facing capability to search X posts, but the code also accesses local process environment state to retrieve a secret API key. While this is a common implementation pattern, credential/env access is not itself part of the stated user-purpose and introduces a capability beyond pure query handling.
This code sends the user-provided query to the xAI Grok API over the network, which is a safety-relevant data transmission. While the file-level docstring says it searches X posts using the xAI Grok API, there is no runtime warning, confirmation, or more explicit disclosure near the transmission path that user query content is being sent to a third-party service.
No suspicious patterns detected.