research-channels
多源研究通道工具箱。当需要检索文献、核验引用、查基准分数、看价格与上下文、找开源实现、扫描社区信号时使用。封装了 arXiv / Crossref / OpenAlex（含引用网络）/ Epoch AI 官方 API / GitHub / Hacker News / Hugging Face / OpenRouter / Vals AI / Scale SEAL / Stanford HAI / ARC Prize / METR 共 14 个通道。触发场景：查文献、验引用、查谁引用了某篇、查某个基准的精确分数、比模型价格、找现成项目、看领域最新动态。
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The skill's required workflow uses search and research commands (such as GitHub, Hacker News, arXiv, and web page scraping) to fetch external literature, community discussions, and project repositories, which can contain outsider-authored free text.
- Repository
arwei944/research-bench
- Revision
ecbb3f4
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.