X Smart Read

PassAudited by ClawScan on May 10, 2026.

Overview

This is a coherent X API analytics skill, but users should understand that it needs X API credentials, can spend API credits, can change bookmarks, and stores social data locally.

Install only if you are comfortable giving the skill X API credentials and letting it cache your X data locally. Use least-privilege API permissions, avoid --force/--no-budget unless you intentionally accept the cost, and approve bookmark changes explicitly.

Findings (5)

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

Anyone using the skill must trust it with X developer credentials and access tokens for their account.

Why it was flagged

The scripts use delegated X API credentials for the user's account. This is expected for the skill's purpose, but it gives the skill account-level API access.

Skill content
tweepy.Client(bearer_token=config.get("bearer_token"), consumer_key=config["api_key"], consumer_secret=config["api_secret"], access_token=config["access_token"], access_token_secret=config["access_secret"]
Recommendation

Use a dedicated X developer app, grant the least privilege needed, protect the local config file, and avoid granting write permissions unless bookmark add/remove features are required.

What this means

Tweets, mentions, bookmarks, usage history, follower history, and credentials can remain on disk after use.

Why it was flagged

The skill persistently stores credentials and X account data locally for caching and cost tracking.

Skill content
Config and data live at `~/.openclaw/skills-config/x-twitter/`: `config.json` — credentials... `data/tweets.json`... `data/mentions.json`... `data/bookmarks.json`... `data/usage.json`
Recommendation

Use this only on a trusted machine, keep the directory private, and delete the skill's config/data directory if you stop using it.

What this means

If an agent or user invokes those flags carelessly, API calls may continue despite daily budget warnings or limits.

Why it was flagged

The skill has documented flags that intentionally bypass cost controls for X API calls.

Skill content
`--force` Override budget guard; `--no-budget` Skip all budget checks and warnings
Recommendation

Require explicit user approval before using --force or --no-budget, and prefer dry-run mode when cost is uncertain.

What this means

The environment may download or resolve package versions when commands are run.

Why it was flagged

Runtime dependency installation is disclosed and central to the skill, but it means execution depends on externally resolved Python packages.

Skill content
All scripts use `uv run` (auto-installs dependencies).
Recommendation

Run it in a trusted environment and consider pinning/locking dependencies if reproducibility is important.

What this means

A user may not immediately realize that bookmark management can modify private account state.

Why it was flagged

The README mainly frames the skill as read access, while it also includes user-directed bookmark write actions.

Skill content
Give your AI agent read access to X ... `x_bookmarks.py add ID` | Bookmark a post
Recommendation

Treat bookmark add/remove as write actions and only let the agent perform them when explicitly requested.