6verity
数学建模竞赛最终验证和验收阶段，支持 Typst 和 LaTeX 双引擎。用于论文写完后检查章节数量、标题顺序、图表引用、数值一致性、占位符、内部文件泄露、参考文献、代码可复现性、编译和提交就绪状态。
61
72%
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/6verity/SKILL.mdLow
Low-risk findings.
1 low severity finding. 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
Outsider free text is read at runtime from project files determined by the user/model (e.g., main paper `main.typ/main.tex`, section files, `references.*`, `PROBLEM_ANALYSIS.md`, `RESULTS_REPORT.md`, `all_results.json`) via `writing_check.sh`’s Python `read(path)` which does `path.read_text()` and then feeds the concatenated content into the script’s LLM-relevant context (by print/log/reporting decisions); there is no isolation ensuring those documents are user-authored.
- Repository
- jihe520/MathModelAgent
- Commit
11f3862
- 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.