Back to skill
Skillv1.0.0

ClawScan security

gamer-news-skill · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignFeb 18, 2026, 4:04 PM
Verdict
Benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's instructions, scope, and resource needs align with its stated purpose of fetching and summarizing gaming RSS feeds; it requests no secrets, has no install steps, and contains no surprising behavior.
Guidance
This skill appears low-risk and coherent: it only fetches public RSS feeds and article pages and asks for no credentials. Before installing, consider that it will make outbound network requests (which reveal the agent's IP to feed hosts and visited sites), may fetch linked content that could include trackers, and will summarize copyrighted articles (ensure that use fits your policy). If you want extra assurance, review the GitHub repo linked in the SKILL.md for any hidden code or recent changes before enabling autonomous invocation.

Review Dimensions

Purpose & Capability
okThe name/description claim to fetch and summarize gaming news and the SKILL.md only requires reading public RSS feeds and (on demand) visiting article URLs — which is exactly what you'd expect for this skill. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
okRuntime instructions are limited to fetching specified RSS feed URLs, parsing feed fields, deduplicating, and optionally fetching article pages for deeper summaries. The instructions do not ask the agent to read local files, environment variables, or send data to unexpected endpoints.
Install Mechanism
okThis is an instruction-only skill with no install spec or code files, so nothing is written to disk or downloaded by the installer. That minimizes on-disk risk.
Credentials
okThe skill declares no required environment variables, credentials, or config paths. Its network access to public RSS feeds and article URLs is proportionate to its purpose.
Persistence & Privilege
okalways is false and the skill is user-invocable (default). It can be invoked autonomously by the agent (platform default) but does not request permanent presence, elevated privileges, or modify other skills or system settings.