系统审计。触发:审查系统、扫描 bug/安全/性能/架构债,产出发现清单。不要用于审查单次改动 diff(cs-code-review)、修已知 bug(cs-issue)、实现功能(cs-feat)、行为等价重构(cs-refactor)、沉淀已知经验(cs-keep);这是仓库级只读投查,只发现不定修。
67
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
The spec requires each finding to include file:line plus the exact code snippet as evidence, which would force the LLM to reproduce any in-code secrets (API keys, tokens, passwords) verbatim in its output.
7bed4ed
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.