Skillv1.0.0

ClawScan security

Build Legal Services FAQ Page · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 22, 2026, 10:23 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This instruction-only FAQ generator is internally consistent with its stated purpose and requests no credentials or installs, but outputs should be human-reviewed for legal accuracy and privacy before use.
Guidance: This skill appears coherent and low-risk, but consider these precautions before using it with real client matters: 1) Always have a qualified attorney or compliance reviewer verify outputs—do not treat generated content as legal advice. 2) Avoid pasting sensitive or personally identifying client data into prompts; web_search or chat calls may transmit content to external services. 3) Confirm jurisdiction-specific accuracy and cite primary sources—web_search results can be incomplete or out of date. 4) If you integrate this into automated workflows, remember the skill can be invoked by the agent (default behavior); keep human checkpoints for high-risk decisions. 5) Ensure any connected chat/web_search providers meet your privacy/compliance requirements before sending confidential material.

Purpose & Capability: okThe name/description (generate legal-services FAQ content) match the instructions: drafting FAQs, clarifying audience/goals, and using chat/web_search. No unrelated binaries, env vars, or credentials are requested.
Instruction Scope: okSKILL.md contains scoped, document-focused steps (clarify audience, draft, refine). It references chat and web_search APIs only and explicitly recommends human review; it does not instruct reading system files, environment variables, or other unrelated data sources.
Install Mechanism: okNo install spec or code files are present (instruction-only), so nothing will be written to disk or fetched at install time.
Credentials: okNo environment variables, credentials, or config paths are required. The declared APIs (chat, web_search) are proportional to producing and fact-checking FAQ content.
Persistence & Privilege: okalways is false and the skill is user-invocable; it does not request persistent system-wide privileges or claim to modify other skills' configs.