Back to skill
Skillv1.0.0

ClawScan security

China Collective Memory · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 14, 2026, 10:25 AM
Verdict
Benign
Confidence
high
Model
gpt-5-mini
Summary
The skill is an instruction-only local reference dataset (Chinese historical memory anchors) and its declared requirements and instructions match the bundled files — nothing requests unrelated credentials, installs, or network access.
Guidance
This skill is a local reference dataset in Chinese and requires no network access, credentials, or installs — you can inspect the included markdown files before enabling it. Note: the content covers politically sensitive historical events and eras; that affects how the agent may generate outputs (potential bias or moderation triggers) but does not imply technical risk. If you plan to let agents invoke skills autonomously, be aware the agent can read the entire dataset and use it in replies; otherwise there are no hidden endpoints or secret exfiltration vectors in this package.

Review Dimensions

Purpose & Capability
okName/description (search & browse Chinese collective-memory anchors) aligns with the included decade-based reference markdown files; all functionality can be implemented by reading/searching the provided files.
Instruction Scope
okSKILL.md limits runtime behavior to browsing and searching the bundled references/ files, and explicitly states no tools, APIs, or storage layer are required; there are no instructions to read unrelated system files, access environment variables, or transmit data externally.
Install Mechanism
okNo install spec and no code files — lowest-risk instruction-only skill. All content is delivered as plaintext markdown files included in the bundle.
Credentials
okThe skill declares no required environment variables, credentials, or config paths; its data-only nature makes this proportional to its stated purpose.
Persistence & Privilege
okalways:false and default autonomous invocation are set (normal for skills). The skill does not request system-wide persistence or modify other skills/config.