X

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

If OAuth is enabled, the skill can keep using the authorized X account and can post publicly through that account until access is revoked.

Why it was flagged

The skill asks for OAuth scopes that can read user-context data, post tweets, and keep refresh access via a locally stored token file.

Skill content

Save tokens to `~/.openclaw/x/tokens.json` ... **Scopes granted:** `tweet.read`, `users.read`, `bookmark.read`, `tweet.write`, `offline.access`

Recommendation

Only enable OAuth if you need bookmarks, likes, or posting; protect the ~/.openclaw/x files, revoke tokens when no longer needed, and consider using a dedicated X app/account.

NoteHigh Confidence

ASI02: Tool Misuse and Exploitation

What this means

A mistaken or over-broad agent instruction could publish content from the connected X account.

Why it was flagged

Posting to X is a high-impact external action, but it is clearly part of the stated feature set.

Skill content

**User context (OAuth 2.0):**
- Bookmarks
- Liked tweets
- Post tweets

Recommendation

Treat posting as a confirmation-required action: review the exact tweet text and account before allowing the command to run.

NoteHigh Confidence

ASI02: Tool Misuse and Exploitation

What this means

Large searches, timelines, or bookmark exports could consume paid API credits.

Why it was flagged

The skill can make API calls that may consume paid X API credits, but the cost model and spending-limit advice are disclosed.

Skill content

**Pay-per-usage model:**
- Buy credits in Developer Console
- Charged per unique tweet/user returned
- Set spending limits to control costs

Recommendation

Set X API spending limits and keep command `--max` values modest unless you intend to spend credits.

NoteHigh Confidence

ASI04: Agentic Supply Chain Vulnerabilities

What this means

You have less external provenance to verify who maintains the skill or where updates come from.

Why it was flagged

The registry entry does not provide an external source or homepage for provenance verification, although the included artifacts show no remote installer or dependency chain.

Skill content

Source: unknown
Homepage: none

Recommendation

Review the included script before use and prefer installing from a trusted publisher or repository when available.