magnet-searcher
PassAudited by ClawScan on May 13, 2026.
Overview
The skill is coherent and instruction-only, but it asks for unpinned browser-automation setup and browsing untrusted magnet/torrent sites, so review those steps before use.
Before installing, confirm you trust the browser automation tooling and package sources, consider using an isolated browser/profile, do not provide credentials on magnet sites, and only search/download content you have rights to access.
Publisher note
Search for movies, TV shows, or other content and find magnet/torrent download links. Use this skill whenever the user asks for movie downloads, torrent links, magnet links, BT downloads, or wants to find download sources for specific content. This skill uses agent-browser to navigate magnet search sites and extract working magnet URLs. Trigger whenever the user says things like "find magnet link for X", "search for movie X torrent", "find the download link for X", "帮我找X的磁力链接", etc.
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.
Installing these tools can change the local system and depends on the current npm/package-manager sources.
The skill relies on manually installed, unpinned global/npm/system browser tooling rather than a pinned install spec. This is disclosed and central to browser-based searching, but it expands supply-chain and provenance exposure.
npm install -g agent-browser ... apt-get install -y chromium ... agent-browser install
Install only from trusted package sources, prefer pinned versions where possible, and review agent-browser and Chromium provenance before use.
The agent could land on unsafe or misleading pages while looking for magnet links.
The core workflow uses browser automation to visit magnet/search sites, click search results, and run JavaScript in the browser. This is purpose-aligned, but the destination pages and search results are untrusted.
agent-browser open "https://btsow.pics"
...
agent-browser click @e36
...
agent-browser eval "document.querySelector('a[href*=magnet]')?.href"Keep the task narrowly scoped, avoid entering sensitive information on these pages, and verify any resulting links before using them.
A malicious or spammy page could try to influence the agent during the current browsing task.
The workflow may bring arbitrary text from external pages into the agent context. This is needed for search/extraction and is not persistent memory, but untrusted page text should not be treated as instructions.
agent-browser snapshot ... agent-browser eval "document.body.innerText" # Get all text, then search manually
Treat webpage text as data only, ignore any page instructions aimed at the agent, and use the content only to identify the requested magnet link.