Skill Trust Decision
daily-memory-summary
SKILL.md 声称仅"合并内容写入每日memory"，但 scripts/summarize.sh 实际还包含未声明的联系人身份解析功能（从通知数据提取邮箱/姓名/团队信息），存在文档欺骗和阴影功能。
Most direct threat evidence
Why this conclusion was reached
1/4 dimensions flagged Block
Declared vs actual capability
1 undeclared or violating capabilities were inferred.
Review
Hidden execution and egress
2 lower-risk artifacts were extracted and still need context.
Pass
Attack chain and severe findings
There is no explicit malicious chain in the report.
Review
Dependencies and supply chain hygiene
Dependency information is incomplete, so supply-chain confidence stays limited.
What drove the risk score up
阴影功能-联系人解析 +25
代码提取联系人邮箱/姓名/团队但SKILL.md未声明
敏感数据预览 +10
stdout预览可能暴露剪贴板/通知中的密码token
硬编码敏感路径 +5
直接访问~/.openclaw/workspace下文件
Most important evidence
Medium Doc Mismatch
SKILL.md 未声明联系人解析功能
scripts/summarize.sh 第42-50行使用grep从通知数据中提取联系人身份（邮箱、姓名、团队），但SKILL.md仅描述为"合并内容写入memory"，未提及此功能。skill-card.md虽提到此风险但未在主文档中声明。
scripts/summarize.sh:42-50 在SKILL.md功能描述中明确列出"解析通知中的联系人身份"步骤
Medium Data Exfil
stdout预览可能暴露敏感剪贴板内容
scripts/summarize.sh 第77行执行 `head -30 "$OUTPUT_FILE"` 将memory预览输出到stdout，可能在终端日志中留下密码/token/私人消息痕迹。
scripts/summarize.sh:77 移除预览输出或改为仅输出非敏感状态信息
Low Sensitive Access
硬编码访问特定工作区路径
脚本硬编码访问 /Users/wutianfu/.openclaw/workspace/... 路径，非通用技能设计。
scripts/summarize.sh:5 使用环境变量或参数化路径增强可移植性
Declared capability vs actual capability
Filesystem Pass
Declared READ
→ Inferred WRITE
scripts/summarize.sh:34-55 读取clipboard/notification Filesystem Pass
Declared WRITE
→ Inferred WRITE
scripts/summarize.sh:64-74 写入memory文件 Shell Block
Declared NONE
→ Inferred WRITE
scripts/summarize.sh:42-50 使用grep/ls等shell命令 Clipboard Pass
Declared READ
→ Inferred READ
SKILL.md声明读取clipboard数据 Suspicious artifacts and egress
Medium External URL
https://clawhub.ai/user/gift-is-coding skill-card.md:9
Medium External URL
https://clawhub.ai/gift-is-coding/skills/daily-memory-summary skill-card.md:39
Dependencies and supply chain
There are no structured dependency warnings.
File composition
4 files · 183 lines
Markdown 2 files · 94 linesShell 1 files · 84 linesJSON 1 files · 5 lines
Files of concern · 2
skill-card.md https://clawhub.ai/user/gift-is-coding · https://clawhub.ai/gift-is-coding/skills/daily-memory-summary
scripts/summarize.sh SKILL.md 未声明联系人解析功能 · stdout预览可能暴露敏感剪贴板内容 · 硬编码访问特定工作区路径
Other files · SKILL.md · _meta.json
Security positives
skill-card.md 主动披露了已知风险（存档密码token、联系人解析、stdout暴露）
代码逻辑清晰，无恶意混淆或编码
无外部网络请求或数据外传
无凭证收割或反向shell