Skillv1.0.0

ClawScan security

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

BenignApr 29, 2026, 12:05 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only, read-only reference about Twitch that requests no installs, credentials, or system access — its declared capabilities match its requirements.
Guidance: This skill is low-risk: it is a static reference document about Twitch and asks for no credentials or installs. If you install it, understand it only provides knowledge the agent can reference; verify any factual claims (numbers, revenue, policies) against authoritative sources because the document may be dated or contain summarization bias. Also note that the skill can be invoked autonomously by agents by default — which is normal — but if you combine this skill with others that have broader permissions, review those other skills' requests before enabling autonomous use.

Purpose & Capability: okThe skill's name and description promise informational content about Twitch; the skill requests no binaries, environment variables, or installs, which is appropriate for a knowledge/reference skill.
Instruction Scope: okSKILL.md is a long-form informational document with 'read_when' contexts; it does not instruct the agent to run commands, read system files, access credentials, or send data to external endpoints. Scope stays within providing background and analysis about the platform.
Install Mechanism: okNo install specification or code files are present. Being instruction-only means nothing is written to disk and there is no install-time risk.
Credentials: okThe skill declares no required environment variables, credentials, or config paths. There is no disproportionate request for secrets or unrelated access.
Persistence & Privilege: okalways is false (normal), user-invocable true, and model invocation is allowed (default). These are standard for skills and are not excessive given this skill's read-only nature.