Security audit
Security checks for vulnerabilities and agentic risk
This skill does what it claims: it sends X/Twitter search queries to xAI using the user's API key and returns summarized public-post results.
Install this only if you are comfortable sending your X/Twitter search queries and related filters to xAI under your API key. Avoid searching for secrets, private internal names, regulated data, or other sensitive terms unless that is acceptable under your own data-handling rules.
The skill invokes Python, reads an API key from the environment, and sends user queries to an external service, but it does not declare an explicit tool scope such as permissions or allowed-tools. That weakens least-privilege controls and makes it harder for a host to constrain or transparently authorize the skill’s access to environment data and network egress.
The description contains broad trigger phrases like wanting to 'find tweets,' 'search X/Twitter,' or 'look up what people are saying,' which can match many ordinary requests. Over-broad routing can cause unintended invocation of a networked skill, leading to unnecessary data disclosure to the external API or use of the wrong tool without clear user intent.
The documentation explains setup and usage but does not clearly warn that user-supplied search terms are transmitted to the xAI API for processing. In a search skill, queries may contain sensitive topics, internal names, or personal data, so omission of this disclosure increases privacy and compliance 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
The manifest frames this skill as searching X posts via the xAI API, but the code also accesses a local environment secret (XAI_API_KEY) to operate. While this may be implementation-required, credential retrieval is a capability beyond the user-facing search purpose and is not described in the manifest.
No suspicious patterns detected.