Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed skill-review helper with limited local scripts; its optional auto-fix behavior is narrow and purpose-aligned.
Install only if you are comfortable with a Chinese-language skill that can run local Python scripts against a skill directory. Use the single-pass analyzer for read-only review; run the review-loop only when you want it to create missing standard directories in the target skill.
The declared purpose says the skill is for review and optimization guidance, but the body includes behaviors that can execute scripts, iterate review-fix loops, and potentially modify the target skill directory. This mismatch is dangerous because users or orchestration layers may treat the skill as advisory while it actually performs write-capable or autonomous actions on the filesystem.
Referenced artifact was not completely inspected
- 目录必须包含 `SKILL.md` 文件
The skill description, headings, trigger phrases, and workflow are all presented only in Chinese, which implies a fixed language requirement. Under the policy, language constraints should either be optional for the user or clearly justified as region-specific; neither is stated here.
The skill instructs use of code-capable actions such as reading files and running shell commands, but it does not declare any tool scope or allowed-tools boundary. That creates an authorization ambiguity where an agent may invoke broader capabilities than users expect, increasing the chance of unsafe file-system inspection or command execution during review tasks.
The skill's user-facing description is written entirely in Chinese and specifies its activation/use context in Chinese, with no indication that other languages are supported or that the user can choose a preferred language. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is explicitly justified.
The manifest uses Chinese for the skill name, description, and category, with no indication that language selection is optional or that the skill is intended only for a Chinese-language environment. This can violate a language/locale policy when users are not given an explicit opt-in or documented justification for the constraint.
The entire skill reference is written as a prescriptive template in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context. Per the policy, forcing a specific language without opt-in is a natural-language locale violation.
The file’s docstring, usage text, comments, and generated report strings are all hard-coded in Chinese, indicating the skill operates in a specific language by default. The policy allows locale constraints only when user choice or clear justification is provided, which is not present here.
The module docstring presents the script description, usage, and examples entirely in Chinese, and all user-facing output strings in the file are likewise Chinese-only. This constitutes a language-policy issue because the skill hardcodes a single language without offering a user opt-in or documenting that the tool is intentionally region-specific.
This Python file contains all docstrings, help text, status messages, and error messages in Chinese, including the CLI description and runtime output. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
(是否有问题, 输出内容)
"""
script_path = Path(__file__).parent / "analyze.py"
result = subprocess.run(
[sys.executable, str(script_path), str(skill_path)],
capture_output=True,
text=True
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
(是否有问题, 输出内容)
"""
script_path = Path(__file__).parent / "analyze.py"
result = subprocess.run(
[sys.executable, str(script_path), str(skill_path)],
capture_output=True,
text=True
No suspicious patterns detected.