wewrite-learn
WeWrite 自学习模块：从用户的人工修改中学习写作偏好（playbook 飞轮）、导入范文建风格库、 从公众号文章学习排版主题。 触发关键词：学习我的修改、我改了学习一下、导入范文、学习这篇文章、查看范文库、 学习排版、学排版。 不应被通用的"学习"、"总结这篇文章"触发——需要公众号/WeWrite 上下文。
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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
SKILL.md 运行路径中，用户可触发“学习这篇文章/导入范文 + URL”为 `wewrite fetch-article <url>`，随后内容作为 `/tmp/article.md` 被 `wewrite exemplar /tmp/article.md` 读入并注入写作模块的初稿 prompt；该路径会把第三方网页抓取的自由文本（URL 站点正文）带入 LLM 上下文，属于 public web content fetched at runtime。
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill accepts and fetches arbitrary external content via the user-supplied URL ("<url>") at runtime (e.g., `wewrite fetch-article <url> ...` and `wewrite learn-theme <url> ...`) and then injects that fetched content into exemplars/prompts, so external content can directly control the agent's prompts.
- Repository
- imraywang/wewrite
- Commit
ed8b083
- 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.