AI Berkshire skill: 财报精读:一手资料深度解读. Source: skills/earnings-review.md.
69%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./codex-skills/earnings-review/SKILL.mdThe 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)。
xbtlin/ai-berkshire
bea57d5
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.