Skillv1.0.0

ClawScan security

中文商务邮件写作助手 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 16, 2026, 2:35 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill is an instruction-only Chinese business email writing assistant whose files and runtime instructions match its stated purpose and request no extra privileges or installs.
Guidance: This skill appears coherent and low-risk: it only provides templates and guidance for writing Chinese business emails. Before using, avoid pasting sensitive secrets or private credentials into prompts (the skill will include any text you give it in generated messages). When using outputs as actual email text, review for correctness, company policy compliance, and recipient appropriateness. If you plan to let an autonomous agent invoke skills, be aware the agent could generate or suggest full emails automatically—ensure you trust the agent's scope and review any automated sends.

Purpose & Capability: okName, description, and included reference files (templates, phrase guide, subject-line guide, SKILL.md) all align with a Chinese business email drafting/ polishing assistant; there are no unrelated requirements (no credentials, binaries, or config paths).
Instruction Scope: okSKILL.md contains structured guidance, templates, tone-adjustment rules, and a check-list. It does not instruct reading system files, accessing environment variables, contacting external endpoints, or exfiltrating data.
Install Mechanism: okInstruction-only skill with no install spec and no code files to write to disk; lowest-risk install posture.
Credentials: okNo environment variables, credentials, or config paths are required. The skill's functionality reasonably requires only the user-provided email content/context at runtime.
Persistence & Privilege: okalways is false and there is no indication the skill modifies system or other skill configurations. It does not request permanent presence or elevated privileges.