Skillv1.0.1

ClawScan security

Twitter Agent · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 10, 2026, 5:32 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill's code, environment requirements, and runtime instructions match its stated purpose (automating Twitter/X posting using tweepy and an external 6551 service for topic discovery).
Guidance: This skill appears internally consistent: it needs your Twitter OAuth keys (read+write) so it can post/reply/quote on your behalf, and it needs a TWITTER_TOKEN to call the ai.6551.io service for trending content. Before installing: 1) ensure you trust the 6551 service (ai.6551.io) because the skill will send requests to it using your TWITTER_TOKEN; 2) be aware the skill will have write access to your Twitter account — only install if you trust the skill and its operator; 3) credentials should be stored securely and you should be prepared to revoke them if unexpected posts appear; 4) note SKILL.md requires the agent to exec shell commands (run scripts and curl), which is necessary for operation but gives the agent the ability to perform those network and file actions; and 5) there is a minor metadata inconsistency about install instructions (SKILL.md asks to pip-install tweepy) — confirm OpenClaw will install that dependency or install it yourself before use.

Review Dimensions

Purpose & Capability: okThe skill is a Twitter automation agent and requires Twitter OAuth keys and tokens; the included Python scripts use those exact credentials and tweepy to post/reply/quote. The extra TWITTER_TOKEN is used by SKILL.md to call the 6551 API for trending content, which fits the stated 'hot topic fetching' capability.
Instruction Scope: noteSKILL.md expects the agent to exec shell commands (run the provided Python scripts and curl calls). That is normal for an operational skill but gives the agent the ability to perform those shell calls autonomously. The only external network endpoints referenced are developer.x.com (docs), api endpoints at ai.6551.io (for topic fetch), and standard Twitter/X APIs; the scripts themselves only read the declared Twitter env vars and do not attempt to read other system files.
Install Mechanism: noteThe package is instruction-only in the registry, but SKILL.md includes an 'install' entry to pip-install tweepy. Using pip to install the well-known 'tweepy' package is proportionate. No downloads from untrusted URLs or archive extraction are present. Slight inconsistency: registry metadata reported 'No install spec' while SKILL.md declares a pip install; this is likely benign but worth noting.
Credentials: okThe required env vars are the four Twitter OAuth 1.0a credentials (consumer key/secret and access token/secret) plus a TWITTER_TOKEN for the 6551 service; each is justified by the skill's functions (posting/replying/quote needs write credentials; trending fetch needs 6551 token). No unrelated credentials or unexplained secret access is requested.
Persistence & Privilege: okSkill is not always-included (always: false) and is user-invocable; it does not request system config paths or modify other skills. Autonomous invocation is allowed (disable-model-invocation:false) which is the platform default — acceptable here but remember it lets the agent run the scripts without further prompts.