AI Meeting Room
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is coherent and purpose-aligned, but users should notice that it automatically performs web searches and may reuse prior meeting context.
This skill appears safe to install as an instruction-only advisory tool. Before using it, remember that it may run web searches automatically and may continue from earlier meeting context; avoid sharing confidential information unless you are comfortable with that use, and verify important legal, financial, or strategic claims independently.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The user’s topic may be sent as web search queries, and the agent may spend tool/cost budget on several searches.
The skill directs the agent to run multiple web searches automatically and begin without a separate confirmation step. This is purpose-aligned for data-backed meetings, but it is still external tool use users should notice.
주제가 들어오면 회의 시작 전 **web_search 실행** ... **스프린트:** 3~5회 검색 ... **풀/딥:** 8~12회 검색 ... 사용자에게 안내 후 바로 시작 (확인 불필요)
Do not include confidential business plans, private customer data, or sensitive internal details unless you are comfortable with them being used for web research.
Information from earlier meetings may influence later advice, including details the user did not intend to reuse.
The skill tells the agent to reuse previous meeting context automatically. That can help continuity, but it can also carry forward stale, sensitive, or user-unreviewed context.
연속 회의 체크: 이전 회의 맥락이 있으면 자동으로 이어받기
Ask the agent to summarize the carried-over context before relying on it, and start a fresh meeting for unrelated or sensitive topics.
The simulated experts may sound more authoritative than the model’s actual reliability supports.
The skill uses authoritative expert personas with prestigious backgrounds. The artifacts frame them as AI personas, so this is not deceptive by itself, but users should not treat the output as advice from real licensed professionals.
각 에이전트는 **구체적 배경**을 가진다 ... **신뢰할 수 있는 전문가 페르소나**
Use the output as brainstorming or decision support, and verify legal, financial, medical, or investment claims with qualified professionals and primary sources.