Back to skill

Security audit

blog-mini-kit-liufei

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed blog API client, but it enables weakly protected content changes, deletions, uploads, and admin-token use that should be reviewed before installation.

Install only for a trusted blog API that you administer. Prefer HTTPS, change any default admin credentials before use, avoid putting passwords or tokens directly in shell commands, and require explicit user confirmation before delete, hard-delete, upload-delete, or admin bulk-delete actions.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (3)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/blog-mini-kit-liufei.py:103
Finding

Sensitive Credentials and Data May Be Transmitted over Plaintext HTTP

Content
View full analysis
").strip().rstrip('/') if not base_url: print("错误:API 地址不能为空", file=sys.stderr) sys.exit(3) if not (base_url.startswith("http://") or base_url.startswith("https://")): print("错误:地址必须以 http:// 或 https:// 开头", file=sys.stderr) sys.exit(3) ``` ```python def _api_request(method, path, payload=None, params=None, files=None): """调用目标系统 REST API。""" import requests base_url = _get_base_url() creds = _load_credentials() auth_result = _build_auth(creds) api_key_param = auth_result.pop("_api_key_param", None) api_key_value = auth_result.pop("_api_key_value", None) if api_key_param and api_key_value: params = dict(params or {}) params[api_key_param] = api_key_value auth_kwargs = auth_result url = f"{base_url}{path}" try: if method == 'GET': resp = requests.get(url, params=params, timeout=30, **auth_kwargs) elif method == 'POST': if files: resp = requests.post(url, files=files, timeout=30, **auth_kwargs) else: resp = requests.post(url, json=payload, timeout=30, **auth_kwargs) ``` ```python def cmd_admin_login(args): """能力 AA:后台登录获取 token""" import requests base_url = _get_base_url() url = f"{base_url}/admin/login" try: resp = requests.post( ...[truncated 2093 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/blog-mini-kit-liufei.py:659
Finding

Passwords and Administrator Tokens Are Exposed through Command-Line Arguments

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:178
Finding

Default Administrator Credentials Are Publicly Documented and Demonstrated

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (56)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

该技能与博客 API 管理主题总体相关,大部分已声明的博客资源类型也确有覆盖,因此不是完全偏题。但存在多处实质性描述偏差:1) 描述强调“全部 32 个 API 端点”,而代码头部与实现都表明只有 28 个子命令加 capability-list,且未见 32 个实际端点的完整覆盖;2) 描述明确包含“前端页面”,代码仅访问 /health、/api/* 和少量 /admin/* 接口,没有任何前端页面管理/渲染相关操作;3) 描述写“无认证”,但代码含 admin-login,并将 token 传给后台删除接口,这与“无认证”不一致,至少对后台能力不是无认证;4) 代码是一个命令行 API 客户端封装,不是博客系统本体或其全部端点实现。综上,应判定为描述与实际行为存在明显不匹配。

Content

No source excerpt is available for this finding.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
89% confidence
Finding

The skill explicitly supports hard deletion via DELETE /api/articles/{id} with soft=false and presents it as a routine option. In this skill's context, which lacks strong approval and authorization safeguards, that creates a clear risk of destructive tool misuse and irreversible data loss.

Content

Scanner excerpt · SKILL.md (reported line 204)May include surrounding context.

md
1. **API 不可达。** 先 `curl {base_url}/health` 确认可达,检查 base_url 是否正确。
2. **标签路径拼写为 lables(非 labels)。** API 实际路径是 `/api/lables`,子命令用正确拼写 `create-lable` 但内部请求用 `/api/lables`。
3. **DELETE /api/articles/{id} 默认软删除。** 需要硬删除时传 `soft=false`(子命令用 `--hard` 标志)。
4. **文件上传必须用 multipart/form-data。** curl 用 `-F "file=@path"`,不能用 `-d` JSON。
5. **后台管理需 token。** 先调 `admin-login` 获取 token,再传给 `admin-delete-articles --token`。
6. **GET /api/articles/heat/top 路径冲突。** FastAPI 路由匹配 `/api/articles/heat/top` 优先于 `/api/articles/{id}`,无需担心 ID 被解析为 "heat"。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 215)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 225)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 233)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 241)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 251)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 259)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 267)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 275)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 283)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 291)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 299)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 307)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 315)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 323)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 331)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 339)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 347)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 355)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 363)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 371)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 396)May include surrounding context.

md
python3 scripts/blog-mini-kit-liufei.py health-check

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
97% confidence
Finding

The documented article deletion endpoint supports both soft and hard delete, and in the context of this skill the API is described as unauthenticated. That makes a simple parameterized request sufficient to destroy content, including irreversible deletion when soft=false, which is a direct integrity risk.

Content

Scanner excerpt · references/api-reference.md (reported line 150)May include surrounding context.

{"code":200,"message":"文章更新成功"}

text

#### 5. DELETE /api/articles/{article_id} — 删除文章(支持软删/硬删)

**Path 参数:** `article_id` (int, 必填)
**Query 参数:**

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% confidence
Finding

A delete-by-ID comment endpoint becomes dangerous when paired with the documented lack of authentication because any caller can remove arbitrary comments. This enables censorship, moderation abuse, and loss of discussion integrity with minimal effort.

Content

Scanner excerpt · references/api-reference.md (reported line 314)May include surrounding context.

{"code":200,"data":[{"id":1,"uid":1,"aid":1,"content":"写得好!","deleted":0,"createtime":"2026-08-24T12:00:00","uname":"admin","img":"img/moren.jpg"}]}

text

#### 14. DELETE /api/comments/{comment_id} — 删除评论(软删除)

**Path 参数:** `comment_id` (int, 必填)