No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by zarazhangrui · Agent Tool · ★ 67
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is lark-minutes-tasks safe to install? View the security audit →
Featured in: Meeting Tools & Transcription
English | 中文 Lark Minutes Tasks An AI agent skill that reads Lark/Feishu meeting transcripts, extracts action items, and actually gets them done. Not just a to-do list generator. The agent executes the tasks for you. What it does You give it a meeting transcript (Lark Minutes URL or meeting notes doc). It: Reads the full transcript Scans for Wake Word commands (phrases you said during the meeting to directly instruct the agent) Extracts every action item, both explicit ("I'll send you that doc") and implied For each item, figures out the best way to execute it (schedule a meeting, draft a message, search for info, create a doc, etc.) Shows you a numbered list. You pick which ones the agent should handle. Executes them. Done. Wake Word Set a trigger phrase (like "hey agent" or anything you want). Say it during a meeting, and the agent will pick up your command from the transcript after the meeting. You don't need to remember what you said. The agent remembers for you. Install Drop into your agent's commands directory: Claude Code: Other agents: Place the file wherever your agent reads skill/command definitions from.
| Stars | 67 |
| Forks | 13 |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 66.0223020482145/100 |
| Open Issues | 1 |
| Last Updated | 2026-03-31 |
| Created | 2026-03-30 |
| Est. Tokens | ~2k |
Explore other popular agent tool tools:
lark-minutes-tasks is AI agent skill: read Lark meeting transcripts, extract action items, and actually get them done. It is categorized as a Agent Tool with 67 GitHub stars.
You can find installation instructions and usage details in the lark-minutes-tasks GitHub repository at github.com/zarazhangrui/lark-minutes-tasks. The project has 67 stars and 13 forks, indicating an active community.
lark-minutes-tasks is released under the MIT license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: