AI Berkshire skill: 财报精读:一手资料深度解读. Source: skills/earnings-review.md.
56
63%
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 ./codex-skills/earnings-review/SKILL.mdLow
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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.
SKILL.md 要求运行时通过 Task 工具从公司IR/SEC EDGAR/港交所披露易/巨潮资讯网以及 Seeking Alpha、雪球等“获取原始材料”,这些属于运行时抓取/读取的公共网页或第三方社区内容,会成为可读的自由文本进入LLM上下文(间接提示注入风险)。
634a399
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.