Twitter Autopilot

Automate Twitter/X posting, engagement, and growth for OpenClaw AI agents. Use when setting up an agent's Twitter presence, posting tweets, running engagemen...

This skill appears to do what it says (automate Twitter/X posting) and includes a usable Python script, but pay attention to these points before installing: - Metadata mismatch: The registry claims no required env vars, yet SKILL.md and the script require sensitive Twitter credentials (API key/secret and access token/secret, optional bearer token). Treat that as a red flag — the platform's permission UI may not surface these needs. - Real-world effects: If you supply live account credentials and allow autonomous invocation, the agent can post, follow, unfollow, delete, and otherwise act on your public account. Run in DRAFT mode or use a separate test account until you trust it. - Secrets handling: Only provide keys you are willing to revoke. Prefer a dedicated API key/token pair with minimal permissions. Rotate tokens after testing. Do not use credentials tied to a high-value or organizational account. - Review and limit autonomy: If possible, require human approval (MODE.md DRAFT) for initial posts, or disable autonomous cron jobs. Audit logs in twitter/posted-log.md regularly. - Code review: The included script looks straightforward and contains no obvious remote exfiltration or obfuscated endpoints, but confirm that log paths and files are acceptable for your environment and that you are comfortable with the script writing to disk. If you want to proceed: update the registry metadata to declare the required environment variables (so reviewers and automated gates can surface them), test against a disposable/test account, and enforce draft approval until behavior is verified.

Type: OpenClaw Skill Name: twitter-autopilot Version: 1.3.1 The skill is classified as suspicious due to a local file inclusion/arbitrary file read/write vulnerability in `scripts/tweet.py`. Specifically, the `queue`, `mode`, and `check-dupe` commands can accept arbitrary file paths as arguments, allowing an attacker or a misconfigured AI agent to read or write files outside the intended `twitter/` directory (e.g., `python tweet.py queue /etc/passwd`). While the `SKILL.md` documentation does not instruct the agent to exploit this, the underlying code lacks input validation for these paths, presenting a clear security risk without evidence of intentional malicious design.