Incomplete referenced artifact analysis
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - **署名**:报告结尾固定带 `—— 会勇禾口王的AI笔记 · @huiyonghkw`。命令行 `check.py` 的报告页脚已内置该署名。
Security audit
Security checks for vulnerabilities and agentic risk
ClawScan’s verdict is benign with medium confidence: the scanners found no decisive sign of harmful behavior, but SkillSpector’s review was partial, so some evidence remains incomplete.
The verdict is benign, but confidence is medium and the scan was partial: 17 of 19 components were fully inspected, two were partially inspected, and obfuscated text plus a bounded parser limit left some checks incomplete. Consider whether you are comfortable with that coverage and with the environment-variable access and Docker image references before installing.
Referenced artifact was not completely inspected
- **署名**:报告结尾固定带 `—— 会勇禾口王的AI笔记 · @huiyonghkw`。命令行 `check.py` 的报告页脚已内置该署名。
Referenced artifact was not completely inspected
- **免费(开源内核)**:`check.py` 的**文本 / JSON 报告 + 评分**。任何人本地或进 CI 随便跑。
Referenced artifact was not completely inspected
所以它是**可选叠加档、不进默认流程**——`check.py` 的零依赖卖点不受影响,不跑也能出完整体检报告。
Referenced artifact was not completely inspected
2b. **深度安全扫描(可选 · 外部工具 SkillSpector)**:`check.py` 的 #0 只做密钥正则;当要查**提示注入 / 数据外泄 / 隐藏指令 / 供应链 / 过度授权 / MCP 越权**等 68 类模式时,叠加跑 [SkillSpector](https://github.com/NVI
Referenced artifact was not completely inspected
**第三方 skill 只在一次性沙箱/容器里跑**,并用最小权限的 Claude 凭据;默认体检只走 `check.py`。
Referenced artifact was not completely inspected
- **`check.py` 不依赖它**,零依赖那条卖点不受影响;这一档是叠加的,不跑也能出完整体检报告。
Referenced artifact was not completely inspected
5. **提出代重构**:问用户要不要直接改(瘦身 SKILL.md、拆 references/、外置 scripts/、把硬路径换成 `~`/相对路径、补 description 触发句)。**得到同意再动文件**,一次改一类、可回退;改完**重跑 `check.py`** 给前后对比分数。
Referenced artifact was not completely inspected
- 改完**重新跑一次 `check.py`** 给前后对比分数。
The skill uses 'env' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
"""密钥文件永远不打开:扩展名规则 + 名称规则双保险。"""
base = os.path.basename(rel).lower()
return (
base == ".env" or base.startswith(".env.") or
base.endswith((".key", ".pem")) or "secret" in base
)
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
# 这些文件必须存在,但 Doctor 不能打开它们。
fake_prefix='sk-'
fake_suffix='ant-should-not-be-read-123456789012345'
printf 'api_key="%s%s"\n' "$fake_prefix" "$fake_suffix" > "$TMP/nested/.env"
printf 'api_key="%s%s"\n' "$fake_prefix" "$fake_suffix" > "$TMP/nested/private.secret.txt"
if ! python3 "$CHECK" "$TMP/nested" --json > "$TMP/nested.json"; then
Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.
def build_env(extra=()):
"""子进程最小环境:只放 claude CLI 跑起来必需的变量。"""
keep = ENV_ALLOW | set(extra)
return {k: v for k, v in os.environ.items()
if k != "CLAUDECODE" and (k in keep or k.startswith(ENV_ALLOW_PREFIX))}
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
fake_prefix='sk-'
fake_suffix='ant-should-not-be-read-123456789012345'
printf 'api_key="%s%s"\n' "$fake_prefix" "$fake_suffix" > "$TMP/nested/.env"
printf 'api_key="%s%s"\n' "$fake_prefix" "$fake_suffix" > "$TMP/nested/private.secret.txt"
if ! python3 "$CHECK" "$TMP/nested" --json > "$TMP/nested.json"; then
echo '❌ BOM + 嵌套 metadata 的合法 Skill 被阻断'
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
The report-generation step explicitly instructs “中文输出” (output in Chinese), regardless of the user's preferred language. The skill provides neither a language opt-in nor a locale-specific justification for this restriction.
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
# 剥掉 CLAUDECODE(否则嵌套调用被守卫拦下),其余只放白名单变量
env = build_env(pass_env)
proc = subprocess.Popen(cmd, stdout=subprocess.PIPE,
stderr=subprocess.DEVNULL,
cwd=project_root, env=env)
buffer, pending, acc = "", None, ""
The frontmatter provides only a name, with no description defining the skill's purpose or invocation scope. Line 10 explicitly acknowledges that the missing description prevents the model from determining when to load the skill.
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
"$TMP/doctors/hekouwang-claude-md-doctor-skill" \
"$TMP/doctors/hekouwang-claude-skill-doctor-skill" \
"$TMP/doctors/hekouwang-env-doctor-skill/scripts"
printf '%s\n' '# fake skill' > "$TMP/project/.agents/skills/example/SKILL.md"
printf '%s\n' \
'import json' \
'import sys' \
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
# 把要体检的 skill 目录只读挂到 /work:
# docker build -t claude-skill-doctor .
# docker run --rm -v "$PWD:/work:ro" claude-skill-doctor
# docker run --rm -v "$PWD:/work:ro" claude-skill-doctor /work --json
ENTRYPOINT ["python3", "/app/check.py"]
CMD ["/work"]
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
# 把要体检的 skill 目录只读挂到 /work:
# docker build -t claude-skill-doctor .
# docker run --rm -v "$PWD:/work:ro" claude-skill-doctor
# docker run --rm -v "$PWD:/work:ro" claude-skill-doctor /work --json
ENTRYPOINT ["python3", "/app/check.py"]
CMD ["/work"]
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
# 拉已钉死 digest 的镜像;工作目录只读挂载(打 v* tag 时 Actions 同步发布到 GHCR)
IMG=ghcr.io/huiyonghkw/hekouwang-claude-skill-doctor-skill@sha256:<发布页当前 digest>
docker run --rm -v "$PWD:/work:ro" "$IMG"
# 或本地自建(Dockerfile 已 FROM python:3.12-slim@sha256:…)
docker build -t claude-skill-doctor .