Skillv1.0.0

ClawScan security

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

BenignMar 23, 2026, 7:07 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only, content-focused skill that provides bilingual information about Taoism and a personal profile; it has no installs, no required credentials, and its declared behavior matches its contents.
Guidance: This skill is instruction-only and appears coherent with its stated purpose, so technical risk is low. Before installing: (1) note that the SKILL.md includes a personal profile and an email address — if you don't want that exposed by the agent when the skill activates, consider removing or redacting it; (2) verify factual accuracy if you need scholarly or authoritative information (the skill is a general introduction, not a primary source); and (3) because instruction-only skills run with the agent, review agent invocation settings if you prefer to limit automatic activation. No credentials or installs are required.

Purpose & Capability: okName and description match the SKILL.md content: the file is a bilingual introduction to Daoism and includes a personal profile. There are no unrelated requirements (no env vars, binaries, or installs).
Instruction Scope: okSKILL.md contains only explanatory content (history, concepts, texts, and a profile). It does not instruct the agent to read local files, access external endpoints, collect system data, or exfiltrate credentials.
Install Mechanism: okNo install spec or code files are present; this is instruction-only so nothing will be written to disk or downloaded during installation.
Credentials: okThe skill declares no environment variables, credentials, or config paths. The personal contact info in the SKILL.md (email) is content, not a required secret.
Persistence & Privilege: okalways is false and disable-model-invocation is false (normal). The skill does not request persistent privileges or modify other skills' configuration.