Security audit
Security checks for vulnerabilities and agentic risk
This skill is a local changelog drafting helper with no network, persistence, or destructive behavior, though its bundled script contains inactive audit modes that are broader than the advertised changelog use.
Install this if you want a Chinese-language local helper for drafting reviewable changelogs from provided release notes or commit summaries. Review inputs for sensitive data before use, and treat the inactive audit modes in scripts/run.py as extra bundled functionality that should not be enabled unless you intentionally want local file inspection.
声明描述聚焦于“整理对外 changelog / release notes”，这是一个文档总结类能力。但代码实现明显是多模式的通用审计/报告工具：会读取 spec.json 决定模式；可递归扫描目录中的文本文件、统计扩展名、抽取 Markdown 标题；可读取 CSV/TSV 并统计字段；可对文件/目录做危险命令、secret、private URL 等正则扫描；还可检查一个 Skill 目录是否包含必需文件并解析 SKILL.md frontmatter。这些能力与 changelog 整理并不等价，且属于未声明的重要扩展能力。虽然在 structured_brief 模式下它可以对输入文本做结构化整理，部分贴近声明用途，但整体主能力实际上取决于外部 spec，范围远超 changelog 工作流，因此描述未准确代表代码实际行为。
The implementation materially diverges from the declared changelog-curation purpose by adding directory auditing, pattern-based security scanning, CSV auditing, and skill-package validation. This scope mismatch is dangerous because users or orchestrators may grant the skill access expecting documentation processing, while the code enumerates and inspects broader local files and repository content than necessary.
The skill advertises executable behavior via python3 and references local input/output files, but it does not declare any explicit tool scope such as allowed tools or permissions. This creates an authorization ambiguity: an agent/runtime may grant broader file or shell access than reviewers expect, increasing the chance of unintended reads, writes, or command execution.
The skill content is written entirely in Chinese and instructs behavior in Chinese, while the manifest description also mixes Chinese with English. There is no indication that the user can choose another language or that the locale restriction is intentionally limited to a region-specific use case, which can violate language/locale policy requirements.
The generated report strings are written in Chinese literals such as '结果', '摘要', and workflow instructions, which imposes a specific language on all users. The file does not provide any option, configuration, or opt-in mechanism for locale selection, so this is a natural-language policy concern.
The pattern_audit capability scans arbitrary files or directories for secrets, internal URLs, and risky shell patterns, which is outside the advertised function of a changelog curator. In this context, the main risk is covert data inspection and unexpected access to sensitive repository contents under a misleading skill identity.
The skill_audit functionality validates package structure and metadata for an entire skill directory, which is unrelated to preparing customer-facing changelogs. While not directly destructive, it expands the operational scope to repository inspection and compliance assessment, increasing the chance of unauthorized analysis or misuse under false expectations.
This markdown file presents all user-facing content in Chinese, but it does not state that the skill is China/Chinese-specific or that users may choose another language. Under the language/locale policy rule, forcing a specific language without opt-in can be a natural-language policy concern.
This markdown file presents all skill instructions and requirements in Chinese, but it does not indicate that the user opted into that language or that the skill is specifically limited to a Chinese-speaking context. Under the policy rule for natural-language violations, forcing a specific language without user choice can be a locale-policy issue.
This markdown file contains only Chinese headings and instructions, which implies a fixed output language. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.
The natural-language metadata is presented only in Chinese for the title and category label, with no indication that users can opt into another language or that the skill is region-specific. Under the policy, forcing a specific language without user choice can be a locale-policy violation.
The entire template, including the title and all section prompts, is written exclusively in Chinese, which implies a fixed output language for the skill. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.
The entire smoke-test document is written only in Chinese, including headings, instructions, and acceptance criteria, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy rule, this is a natural-language locale constraint that is not documented as optional or justified.
