中文 EN

扫描报告

扫描新文件

⚠ 可疑 — 风险评分 50/100
上次扫描：1 天前 重新扫描
50 /100
promptbuddy
智能 Prompt 优化工具 - A prompt optimization skill that transforms user queries into structured prompts
Skill is documentation-only with no implementation files, yet declares execution of an external Python script that doesn't exist in the package, creating an unverified execution vector.
技能名称promptbuddy
分析耗时41.0s
引擎pi
⚠
谨慎使用
Do not use until: (1) Implementation scripts are bundled and verifiable, (2) Script integrity is verified, (3) Permissions are explicitly declared, (4) The 'global forced execution' behavior is justified and documented.

攻击链 4 步

◎
入口 User installs skill expecting prompt optimization
SKILL.md:1
⬡
提权 Attacker places malicious script at ~/.openclaw/workspace/skills/promptbuddy/scripts/smart_engine.py
SKILL.md:8
⬡
提权 Skill executes external Python script on every user input
SKILL.md:8
◉
影响 Malicious script can exfiltrate data, execute arbitrary code, or harvest credentials
~/.openclaw/workspace/skills/promptbuddy/scripts/smart_engine.py

安全发现 4 项

严重性 安全发现 位置
高危
Missing Implementation Files 文档欺骗
The skill declares execution of 'scripts/smart_engine.py' but this script does not exist in the package. Users install this skill expecting prompt optimization, but the actual behavior depends entirely on an external script at ~/.openclaw/workspace/skills/promptbuddy/scripts/smart_engine.py that could be replaced with arbitrary code.
cd ~/.openclaw/workspace/skills/promptbuddy && python3 scripts/smart_engine.py -f json
→ Either include the script in the package with integrity verification, or remove this skill until proper bundling is implemented.
 SKILL.md:8
中危
Undeclared Shell Execution 权限提升
The skill instructs the AI agent to execute shell commands (python3) without declaring shell:WRITE in any allowed-tools section. This is hidden functionality that operates outside the declared capability model.
cd ~/.openclaw/workspace/skills/promptbuddy && python3 scripts/smart_engine.py -f json "用户输入"
→ Declare shell:WRITE permission explicitly if shell execution is required, or remove the execution requirement.
 SKILL.md:8
中危
Hardcoded Framework Path Access 敏感访问
The skill references a specific framework installation path (~/.openclaw) without declaring filesystem access to this path. This path could contain sensitive configuration or user data.
~/.openclaw/workspace/skills/promptbuddy
→ Declare filesystem:READ permission for the required paths, or use a sandboxed execution environment.
 SKILL.md:8
低危
No declared allowed-tools section 文档欺骗
The SKILL.md lacks a standard 'allowed-tools' section that would declare required permissions. According to the capability model, this should map Bash to shell:WRITE.
--- name: promptbuddy
→ Add a proper allowed-tools declaration at the top of SKILL.md.
 SKILL.md:1
资源类型声明权限推断权限状态证据
命令执行 NONE WRITE ✓ 一致 SKILL.md: Executes 'python3 scripts/smart_engine.py' without declaring shell:WRI…
文件系统 NONE READ ✓ 一致 SKILL.md: References ~/.openclaw/workspace/skills/promptbuddy path without permi…

目录结构

1 文件 · 5.1 KB · 145 行
Markdown 1f · 145L
└─ 📝 SKILL.md Markdown 145L · 5.1 KB

安全亮点

✓ No malicious code directly present in the package
✓ No credential harvesting observed
✓ No network exfiltration detected in documentation
✓ No base64-encoded payloads or obfuscation techniques found