安装前评估
prepare-release 评估报告.
为 Agent 提供机器可读的安装决策：任务匹配、Trust Score、Audit Score、安装安全、权限范围，以及在 Skill 进入工作区前的具体验证计划。
需审查中风险审查 策略
78
评估报告
76
信任
84
审计
52
Agent 安全
人工审查
Test manually in an isolated workspace and compare against safer alternatives.
必要关卡
Agent 安装前必须通过的检查
任务匹配度
94
任务描述与此 Skill 的元数据匹配。
- Evaluate prepare-release before installing it in an agent workflow
- 自动化
- Browser automation workflows; Claude Code teams; teams that value GitHub adoption signals
安装路径
92
可用安装交接信息。
- npx skills add CherryHQ/cherry-studio --skill prepare-release
安装命令安全性
92
标准软件包或运行时安装路径
- npx skills add CherryHQ/cherry-studio --skill prepare-release
信任评分
76
Good trust signals with a few areas worth checking before rollout.
- 强候选
- 51K 个 GitHub Stars
- AGPL-3.0
审计评分
84
可安全尝试
- The skill directly executes `pnpm build:builtin-knowledge` and creates git branches/PRs without explicit user confirmation beyond the initial request. This could lead to unintended side effects if the agent is misused or the user input is misinterpreted.
Agent 安全门槛
52
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- Test manually in an isolated workspace and compare against safer alternatives.
- 高风险权限提示：Shell 或命令执行
许可证清晰度
86
AGPL-3.0
- AGPL-3.0
权限范围
62
shell or command execution, filesystem or document access
- Shell or command execution: high
- Browser automation: medium
- Network access: medium
验证计划
Agent 接下来应执行什么
- 1在生产使用前检查仓库、README/SKILL.md、许可证与最近提交。
- 2在没有生产密钥的隔离工作区或沙盒中安装。
- 3运行最小代表性任务，并记录访问的文件、执行的命令、网络访问和输出。
- 4当评估状态为“审查”或“失败”时，至少与一个替代 Skill 比较。
- 5只有在 Agent 报告验证成功且已接受未解决警告后，才提升到更高环境。
不适用场景
需要改用其他 Skill 的情况
- 需要厂商支持 SLA 的团队
- production agents without a repository review
- The skill directly executes `pnpm build:builtin-knowledge` and creates git branches/PRs without explicit user confirmation beyond the initial request. This could lead to unintended side effects if the agent is misused or the user input is misinterpreted.
- 高风险权限提示：Shell 或命令执行
- There is no explicit handling of prompt injection from commit messages or other repository content. While the skill only extracts `release-note` blocks, an attacker could craft commit messages to inject instructions into the release-note generation step (though the LLM is expected to follow the skill's rules).
- Production credentials, payments, or irreversible account changes without explicit human review
辅助检查
支撑该决策的信任信号
README/SKILL.md 完整度
通过86
元数据包含足够的用法与工作流上下文
近期维护
通过88
距上次推送 2 个月
可用替代方案
通过82
有可用于比较的替代 Skill。