xAPI

ReviewAudited by ClawScan on May 10, 2026.

Overview

Review before installing: it is a real-time data/API CLI skill, but it also permits broad third-party API calls, including POST requests that could publish or change external-account data.

Install only if you trust xapi.to and the xapi-to npm package. Keep the API key protected, avoid sending secrets or sensitive private text, and require explicit confirmation before any public, account-changing, or non-read-only API call.

Findings (4)

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.

ConcernMedium Confidence
ASI02: Tool Misuse and Exploitation
What this means

An agent using this skill could make broad third-party API calls and may publish or change external-account data if a mutating endpoint is used.

Why it was flagged

The skill exposes a broad API proxy and documents a POST call that could create public or account-changing content, but the instructions do not require explicit user confirmation or limit the agent to read-only calls.

Skill content
“APIs (`--source api`) — Third-party API proxies” ... “npx xapi-to call x-official.2_tweets --method POST --input '{"body":{"text":"Hello!"}}'”
Recommendation

Require explicit user approval before POST, PUT, PATCH, DELETE, or any account-changing/public action, and prefer read-only endpoints unless the user specifically requests a mutation.

What this means

Anyone with access to the stored API key may be able to use the user’s xapi account or quota.

Why it was flagged

The skill uses a provider API key and stores it locally; this is expected for the xapi integration and is disclosed, but it is still account authority users should protect.

Skill content
“The API key is stored at `~/.xapi/config.json`. You can also set it via `XAPI_API_KEY` env var.”
Recommendation

Use a scoped key if available, protect `~/.xapi/config.json`, and rotate the key if it may have been exposed.

What this means

The behavior depends on the npm package fetched or executed at runtime, which was not available for static review here.

Why it was flagged

The skill relies on an external npm package executed through npx. That is disclosed and purpose-aligned, but the reviewed artifacts do not include or pin the package code.

Skill content
“xapi is available via npx (no install needed): `npx xapi-to <command>`”
Recommendation

Run only if you trust the package source, consider pinning a known version, and review the package separately for sensitive environments.

What this means

Private prompts, text, or identifiers supplied to the CLI may be processed by external services.

Why it was flagged

The skill is designed to send user-provided inputs to xapi and potentially downstream third-party or AI services. This is disclosed and aligned with the purpose, but users should treat submitted text as leaving the local agent context.

Skill content
“Third-party API proxies” and “AI Text Processing” actions such as “chat”, “summarize”, “rewrite”, and “embeddings”
Recommendation

Avoid sending secrets or sensitive private data unless the xapi and downstream service privacy terms are acceptable.