Skills/ClawHub/chat-share-reader

chat-share-reader@0.2.1

CAUTION· static only

Publisher claims: "Export, backup, or archive AI chat conversations to markdown. Two inputs: public share links (ChatGPT, Claude, Gemini, Grok, Perplexity, DeepSeek, Kimi, Qwen, WorkBuddy, biji.com) and 15 local agent session stores (Claude Code, Codex, Cursor, opencode, Cline, Gemini CLI and more). Use when the user asks to save a shared conversation, export the chat they are in now (no args), search past sessions, filter by directory, batch export a site, read a compressed .jsonl.zst archive, or feed a session into another agent. Bulk mode exports your own accounts' history through the browser session you are already signed in to. Tokens are always masked, home paths by default, emails with --redact strict. Also exports biji.com voice notes and transcripts. 导出、备份、归档 AI 对话为 markdown，支持分享链接与本机 15 种 agent 会话记录；不传参数导当前会话，可搜索、筛选、批量导出、读压缩归档、喂给另一个 agent；令牌一律遮，家目录默认遮；另可导出得到笔记录音与逐字稿。" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher mapleleo-hub · publishing for 6 daysInstalls 243Last detonated 4d ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-10 and scored it 67/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

No findings across 4,321 lines in 35 files.

Cost to the agent

Instructions loaded
≈1,381 tok
1 file · 35 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

13 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim mapleleo-hub: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim mapleleo-hubPropose a patch to the maintainer