Skillv1.0.0

ClawScan security

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

Scanner verdict

BenignFeb 20, 2026, 9:55 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill's code and runtime instructions align with its stated purpose (fetching tweet data via FxTwitter and Nitter fallbacks); it requires no credentials and does not attempt unexpected local access, though it will make network requests to third‑party hosts.
Guidance: This skill appears to do what it says: it fetches tweet data via api.fxtwitter.com and falls back to public Nitter instances. Before installing: (1) review the scripts yourself (they're shell scripts and human-readable); (2) be aware that fetching tweets will expose your IP address and User-Agent to the remote host(s) — FxTwitter and any chosen Nitter instance will see those request headers; (3) the Nitter fallback queries multiple community instances (some may be unreliable or untrusted), so if privacy is a concern restrict or remove fallback instances or run the skill only when necessary; (4) verify network access and that curl/jq are up-to-date; (5) test the skill in an isolated environment if you want to avoid contacting third‑party hosts until you've reviewed the code. Overall the skill is internally consistent and does not ask for excessive permissions or secrets.

Review Dimensions

Purpose & Capability: okName/description, SKILL.md, and included scripts all consistently implement tweet extraction using the FxTwitter API as primary source and Nitter instances as fallback. No unrelated binaries, credentials, or config paths are requested.
Instruction Scope: noteRuntime instructions and scripts operate only on the provided tweet URLs and call the documented external hosts (api.fxtwitter.com and listed Nitter instances). Two points to note: (1) the SKILL.md claims 'No external data collection' and 'No telemetry' — while telemetry is absent, any network request reveals requester metadata (IP address, User-Agent) to the remote hosts; (2) the Nitter fallback contacts a list of third‑party instances (community hosts of varying trustworthiness), which may log requests. These are expected for a web‑fetching tool but important privacy considerations.
Install Mechanism: okNo download/install spec; skill is instruction + shell scripts. Nothing is fetched or executed at install time beyond copying files and making scripts executable. This is low risk compared with remote archive installs.
Credentials: okThe skill requests no environment variables or credentials and only depends on common system tools (curl, jq, bash). Scripts do not read other env vars or access unrelated configuration files.
Persistence & Privilege: okSkill does not request always:true or other elevated persistence. Installation is manual (copy scripts into skills folder). It does not modify other skills or system-wide settings.