eval-cs-skill
CodeStable skill 工程化闭环入口。触发：写/改一个 cs skill、评测 skill 效果、跨 model/agent 量化、优化 skill 提示词、把收敛结论固化回 skill。内部推进 author、eval、optimize、release。
71
88%
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
Low
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
源自《SKILL.md》与 runner/buildprompt 的运行路径：`scripts/runner.py` 在每个 fixture 中把 `fixtures/*.json` 里与用户/任务相关的自由文本（如 `fixture.task.spec/diff/context/audit`、`e2e-outcome` 的 `scenario.issue_report`、`learning-transfer` 的 `request`）与被测 `variants/<iter>.md` 快照一起组装为 prompt 并发送给 harness/model，因此外部作者只要能提交/影响 fixtures 或 e2e/learning-transfer 的场景文本就会造成间接 prompt 注入暴露。
- Repository
- codestable/CodeStable
- Commit
19c796d
- 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.