hekouwang-claude-skill-doctor-skill@1.8.4
VERIFIED· install onlyPublisher claims: "体检 Agent Skill：默认 check.py 评 SKILL.md 触发/篇幅/渐进披露/可移植/安全；可选套件可检查项目说明文档与本机开发环境；可选 SkillSpector 深度扫描与 trigger_eval（会把 query/description 发给外部模型）；给评分卡并可代重构" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-10 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
base == ".env" or base.startswith(".env.") orFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- **拔密钥（最高优先）**：#0 命中时把明文移出 SKILL.md / 捆绑文件，改放 `.env` / 密钥管理器；命中即视为已泄露，提醒轮换并查 git 历史（skill 很可能已 push 到 GitHub）。Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.proc = subprocess.Popen(cmd, stdout=subprocess.PIPE,Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.- **绝不读取密钥文件**：`.env` / `*.key` / `*.pem` / `*secret*` 一律不打开（脚本本身也不读）。Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…度误报样本**（别被 90%+ 唬住，这些全部核实为假）：`rm -f "$写死的路径"` → `TM1 Tool Parameter Abuse` 95%；`subprocess.run([...], check=True)` 硬编码列表 → `OH1 Unvalidated Output Injection` 95% + `AST4`（它建议的…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.printf 'api_key="%s%s"\n' "$fake_prefix" "$fake_suffix" > "$TMP/nested/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…put Injection` 95% + `AST4`（它建议的 remediation 恰恰就是这个写法）；docstring 里写"本脚本**绝不读取** .env/*.key" → `PE3 Credential Access`；字体文件名列表 → `MP2 Context Window Stuffing`；中文 fro…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.脚本绝不读取任何 .env / *.key / *.pem 等密钥文件。Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.r"(?i)(x{3,}|y{3,}|your[_\-]?|<[^>]*>|\$\{|\benv\b|process\.env|os\.environ|"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.