Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only developer workflow skill with overly broad activation wording but no hidden execution, persistence, credential handling, or data exfiltration behavior.
Install only if you want a general GitHub/developer workflow helper, and consider tightening or disabling implicit invocation so ordinary requests containing words like run, api, or issue do not accidentally route through this skill.
The skill description and activation guidance are broad enough to match many ordinary software-development requests, which can cause the skill to activate outside its intended scope. Over-broad routing is dangerous because a mismatched skill may provide irrelevant or unsafe workflow guidance, especially in tooling contexts involving code changes, CLI usage, or GitHub operations.
The trigger keywords include very common terms such as 'run', 'api', 'issue', and 'github' without qualifiers, creating a high-collision activation surface. In an agent environment, this can lead to frequent unintended invocation, increasing the chance of incorrect tool selection, prompt hijacking via keyword stuffing, or execution of workflows that do not fit the user's actual request.
触发关键词包含 run、api、github、issue 等高频通用词，且缺少收敛条件，容易在大量无关对话中误触发该技能。误触发会让代理在错误场景下套用本技能流程，造成越权式介入、错误建议或与更合适技能的路由冲突，降低系统可靠性与安全边界清晰度。
The trigger guidance uses a very broad help-request form tied to common developer terms, which can cause the skill to activate for loosely related or unintended requests. Over-broad invocation increases the chance of the agent applying the wrong workflow, leaking irrelevant context into responses, or crowding out a more appropriate skill in safety-sensitive situations.
The trigger phrases are broad, natural-language prompts that overlap with ordinary user requests, which can cause the skill to activate when the user did not explicitly intend to invoke it. In an agent ecosystem, unintended invocation can route tasks into the wrong workflow, increasing the chance of inappropriate actions, confused-deputy behavior, or accidental processing of sensitive repository or issue-management tasks.
The trigger phrases are broad enough to match many ordinary requests, which can cause this skill to activate outside its intended scope. In an agent ecosystem, over-triggering can route users into the wrong workflow, increasing the chance of inappropriate GitHub/CLI-oriented guidance, accidental action suggestions, or confusion that degrades safety and reliability.
The example trigger sentences are truncated and malformed, so they fail to communicate clear and safe activation boundaries to either users or upstream routing systems. Poor examples make misrouting more likely and weaken any safeguard that depends on examples to distinguish this skill from adjacent generic software-help skills.
文件名 SKILL.zh-CN.md 以及全文内容表明该技能面向简体中文环境，但文档中未说明这是可选语言版本、未提供语言切换方式，也未明确限定仅适用于中文用户。这可能构成语言/区域策略上的隐性强制。
技能描述将适用范围扩展到非常宽泛的“software-and-data, github, interact, cli, issue”及“实用流程、产物、检查清单、分析或实现支持”，但没有清晰界定边界或排除场景。这样的模糊触发范围会导致路由器难以准确判定适用性，增加在不合适上下文中调用该技能的概率。
The skill enables implicit invocation while using a very broad description and default prompt, which can cause the agent to select this skill in situations that only loosely match the user’s intent. That increases the risk of unintended activation, context overreach, and execution of GitHub-style workflows or guidance in contexts where the user did not explicitly request this skill.
The trigger guidance lacks concrete scope boundaries and relies on a generic request template, making accidental invocation likely across many unrelated software requests. In an agent-routing context, this can misclassify user intent and route tasks to a skill that may generate actions or advice outside the user's actual need, reducing reliability and potentially affecting safety decisions.
The file lists English and Chinese instruction and README files, but does not state how the user's preferred language is selected. Because language/locale policy violations apply to all file types, this could be read as a language handling policy that lacks explicit user choice.
This is a zh-CN README, but key operational text and all example trigger phrases are presented in English only. That can amount to a language-policy issue because the file appears to force English interaction patterns without explicit user opt-in or a documented bilingual choice.
No suspicious patterns detected.
