Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward X/Twitter search helper that sends the user's query to xAI using the user's API key, with no hidden persistence or unrelated local access found.
Install only if you are comfortable sending search queries to xAI under your own XAI_API_KEY. Avoid putting sensitive private information in queries, and treat API-key configuration in OpenClaw or your environment like any other credential.
The skill invokes Python, requires an API key from the environment, and makes outbound network requests, but it does not declare any explicit tool scope such as permissions or allowed-tools. That creates an avoidable trust gap: the runtime capabilities are broader than what is transparently declared, making review, sandboxing, and policy enforcement harder.
The invocation guidance says to use the skill when the user wants to "look up what people are saying" or "find social media posts about a topic," which are broad natural-language triggers that could match many ordinary requests. The description does not provide exclusion conditions or tighter constraints to distinguish when this skill should or should not activate.
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 reads the XAI_API_KEY from the environment and sends the user's query to an external API endpoint, which is a data-transmitting operation covered by the missing-warning rule for code files. Although the module docstring says it searches X posts using the xAI Grok API, there is no runtime confirmation, prompt, or explicit user-facing warning that the query content will be transmitted to a third-party service along with authenticated credentials.
The test explicitly requires that a handle containing Japanese characters be rejected, which encodes a natural-language/locale constraint into expected behavior. This is a policy concern because it forces ASCII-only input without any user opt-in or documented regional justification in the file.
No suspicious patterns detected.