ljg-paper
Paper reader for non-academics. Finds the load-bearing concepts the reader does not yet truly have, rebuilds them through relations and cases, and turns one paper into a bounded model that explains a concrete phenomenon. USE WHEN the user shares an arXiv link OR paper URL OR PDF OR local paper file OR paper title, or asks to read, explain, analyze, or understand a paper. Defaults to a saved org note. NOT FOR experiment reproduction, exhaustive method summaries, formal peer review, benchmark tables, or literature surveys.
64
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/ljg-paper/SKILL.mdLow
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 的 Workflow Routing 规定会读取“arXiv、PDF、paper URL、本地论文”，并在写作时再读取 template.org；因此运行时会通过对 paper URL/arXiv/PDF 的获取/解析把“论文内容（外部作者文本）”读进 LLM 上下文，属于公网上的/由第三方作者撰写的未由用户选择引入的免费文本输入。
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 explicitly describes runtime fetching of arXiv HTML/assets via WebFetch (e.g., `arxiv.org/html/...`), which would download external paper content/images that are then injected into the agent's context and thus can directly control prompts, so I flag arxiv.org/html/... as a risky runtime dependency.
- Repository
- lijigang/ljg-skills
- Commit
0e78094
- 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.