Skillv1.0.0

ClawScan security

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

BenignApr 29, 2026, 11:06 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This skill is a read-only, instruction-only informational card about Sea Limited; it has no code, no installs, and requests no credentials or system access, so its behavior matches its description.
Guidance: This skill is informational and low risk: it contains a static company overview in Chinese and asks for no credentials or installs. Before relying on its facts for critical decisions, verify key figures and dates against primary sources (Sea Limited filings, official press releases, or reputable financial databases). If you need actionable capabilities (trade, query private APIs, or access accounts), prefer skills that explicitly declare the required credentials and official endpoints.

Purpose & Capability: okThe name/description (Sea Limited company overview) match the SKILL.md content (company history, business lines, metrics). The skill does not request unrelated resources (no env vars, binaries, or config paths).
Instruction Scope: okSKILL.md contains only static informational text and 'read_when' triggers for when the card should be used; it does not instruct the agent to read files, access environment variables, call external endpoints, or perform other side effects.
Install Mechanism: okNo install spec and no code files are present (instruction-only). This is the lowest-risk pattern: nothing is written to disk or installed.
Credentials: okThe skill declares no required environment variables, credentials, or config paths — consistent with an informational/reference card and proportional to its purpose.
Persistence & Privilege: okThe skill is not marked 'always: true' and does not request persistent privileges or modify other skills or system settings. Autonomous invocation is allowed by default but the SKILL.md content is read-only and poses no elevated privilege concerns.