paper-reader
Use when user asks to "read paper", "analyze paper", "summarize paper", "读论文", "分析文献", "帮我看一下这篇paper", "论文笔记", or provides a PDF file that appears to be an academic paper. Specialized for CV/DL papers. Also supports Zotero integration: "读一下这篇论文 ...", "快速看一下这篇论文 ...", "批判性分析这篇论文 ...", "读一下 Zotero 里的 XXX", "批量读一下 Zotero 里 VLA 分类下的论文" **重要触发词**: "读一下 XXX"、"读一下这篇"、"帮我读" → 必须调用此 skill
73
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
High-risk: the daemon sends local PDF paths and metadata to an external "claude" agent using flags that bypass permission checks and instruct it to read/fetch remote content and create/modify local notes and Zotero entries, enabling data exfiltration and remote-driven filesystem/DB modifications.
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
源于用户在 Zotero 中挑选的论文元数据（如 title/arXiv ID/URL）会在 `paper_daemon.py` 中被拼进给 `claude` 的运行时提示，随后该提示要求从外部 arXiv HTML/项目主页等 WebFetch 读取并提取图像与正文内容。
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 constructs runtime prompts that instruct an external model (via the local claude CLI) to WebFetch and use arXiv/DOI URLs such as https://arxiv.org/html/{arxiv_id}, https://arxiv.org/pdf/{arxiv_id}.pdf and https://doi.org/{paper_source['doi']}, meaning external web content is fetched during runtime and can directly influence the agent's instructions/outputs (potential prompt injection risk).
- Repository
- huangkiki/dailypaper-skills
- Commit
a79ff8b
- 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.