适用于 Claude Code 会话的正规评测框架(Evaluation Framework),实现了评测驱动开发(Eval-Driven Development, EDD)原则
47
50%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/eval-harness/SKILL.mdSecurity
1 medium severity finding. This skill can be installed but you should review these findings before use.
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill includes explicit capability tests like "可以创建新用户账户" and the "create-user" test entry which could be interpreted as instructing creation of user accounts (a state-changing action); while the document mostly describes app-level evals, this behavior can potentially lead to actions that modify machine state so it presents moderate risk.
Low
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.
该技能通过在 `.claude/evals/feature-xyz.md` 中读取评测定义/评分器提示(如 Model-Based Grader 的评测代码变更文本与评分指令),属于项目内由用户提交的自由文本作为评测输入被运行时摄取。
dfbf946
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.