xAI / Grok

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

NoteHigh Confidence

ASI03: Identity and Privilege Abuse

What this means

Anyone using the skill is authorizing requests under their xAI account and may incur usage or expose account-scoped access permitted by that key.

Why it was flagged

The script uses the user's xAI API key as a bearer token for xAI API calls. This is expected for the integration, but it grants account/API quota authority.

Skill content

function getApiKey() { return process.env.XAI_API_KEY || null; } ... 'Authorization': `Bearer ${apiKey}`

Recommendation

Use a dedicated xAI API key if possible, keep it out of logs and shared shells, and revoke or rotate it if it may have been exposed.

NoteHigh Confidence

ASI07: Insecure Inter-Agent Communication

What this means

Private prompts, image contents, and search queries may leave the local environment and be processed by xAI according to that service's terms and retention practices.

Why it was flagged

The skill discloses that prompts, selected images, and search requests are sent to xAI. This external provider data flow is central to the purpose and is not hidden.

Skill content

Sends chat prompts to xAI's API at `api.x.ai` ... Vision mode sends images to xAI for analysis ... Uses xAI Responses API with x_search tool

Recommendation

Avoid sending confidential text or sensitive images unless you are comfortable sharing them with xAI under your account and policy requirements.