Twitter Article

PendingStatic analysis audit pending.

Overview

No static analysis result has been recorded yet. Pattern checks will appear here once the artifact has been analyzed.

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.

What this means

If these cookies are mishandled or used unexpectedly, the user’s X account session could be abused to perform account actions beyond the intended article sync.

Why it was flagged

The skill asks the user to provide browser session cookies for Twitter/X. These cookies can represent broad account authority, not just narrowly scoped permission to manage articles.

Skill content
export AUTH_TOKEN="<twitter auth_token cookie>"; export CT0="<twitter ct0 cookie>" ... Cookies 认证:`AUTH_TOKEN` + `CT0`(从浏览器获取)
Recommendation

Use a dedicated account if possible, avoid sharing browser cookies with untrusted code, rotate/logout sessions after use, and prefer a scoped official OAuth/API integration if available.

What this means

A user may install or approve the skill thinking it needs no credentials, then later be asked for highly sensitive browser-session cookies.

Why it was flagged

This registry metadata conflicts with the SKILL.md instructions and code, which require AUTH_TOKEN and CT0 cookies. The credential requirement is materially under-declared.

Skill content
Required env vars: none ... Primary credential: none
Recommendation

Update the metadata to declare the required Twitter/X cookies and Notion key clearly, including the risks and exact scope of what the skill can do.

What this means

Running the wrong command or allowing the agent to run it without review could publicly post or delete article content.

Why it was flagged

The skill exposes commands that can publish or delete X Articles. This is aligned with its purpose, but these are high-impact account mutations.

Skill content
`publish --id <id>` | 发布 ... `delete --id <id>` | 删除
Recommendation

Require explicit user confirmation before publish or delete actions, and verify the target article ID and content before executing those commands.