Security audit
Security checks for vulnerabilities and agentic risk
This is a broad GitHub-style developer workflow helper with noisy activation rules, but it contains no executable code, credential handling, persistence, or hidden behavior.
Install only if you want a general helper for GitHub-style developer workflows. Be aware it may be selected too often because its triggers are broad and implicit invocation is enabled; review its suggestions before allowing code changes or command execution.
The trigger phrases are broad enough to match common user requests and can cause the skill to activate in situations beyond its intended scope. In an agent ecosystem, this increases the chance of unintended tool selection, confusing delegation, or execution of workflows the user did not explicitly request.
The description says to use the skill whenever a user asks for broad categories like software-and-data, github, or interact, which creates an unusually wide activation scope. This ambiguity can make the routing layer invoke the skill in contexts far beyond its intended job-to-be-done, reducing predictability and increasing prompt-scope interference.
The trigger keywords are extremely broad (github, cli, run, api, issue) and are likely to match many unrelated user requests. That can cause unintended skill activation, which increases the chance that this skill overrides more appropriate skills or injects irrelevant workflow guidance into normal conversations.
The trigger sentences are extremely broad and closely resemble ordinary user requests, which can cause the skill to activate in situations far outside its intended scope. Over-broad activation increases the chance of prompt hijacking at the routing layer, unintended invocation, and confused-deputy behavior where the agent applies this skill to unrelated software or GitHub tasks.
The trigger sentence begins with a common phrase ('Help me') and then embeds a long, generic requirement description, making activation boundaries unclear. In agent systems, overly broad triggers can cause unintended invocation in unrelated conversations, leading to misrouting, unexpected tool use, or accidental disclosure of repository-related context when the user did not explicitly request this skill.
The phrase 'I need a practical workflow for ...' is highly generic and could match many ordinary user requests that are not specifically about this skill. Because this skill targets GitHub-style workflows and implementation support, ambiguous triggering increases the chance of accidental activation in broader software discussions, which can expand the skill's reach beyond intended user consent and operational scope.
This file is presented as a Chinese-language README, but core descriptive content is written in English, which can impose a language choice on users without opt-in. That can violate language or locale expectations for localized skill documentation when no alternative or explanation is provided within the file.
The trigger examples are entirely in English despite the file being a Chinese-localized README, which effectively requires English phrasing for activation. Without an explicit language option or justification, this is a locale-policy concern because Chinese-speaking users are not offered equivalent localized triggers.
The example trigger phrases are vague, truncated, and largely restate the broad requirement text instead of showing precise activation conditions. This encourages fuzzy matching and makes it harder for an agent or maintainer to distinguish legitimate invocation from incidental mention of similar terms.
The skill description and usage criteria are very broad, covering generic software, GitHub, CLI, issue, workflow, artifact, checklist, analysis, and implementation support requests. This makes unintended invocation likely, which can cause the agent to route unrelated user requests into this skill and apply guidance outside its intended scope, increasing the chance of inappropriate actions or misleading output.
The trigger keywords include highly generic terms such as 'run', 'api', 'issue', and 'github' without scope constraints or disambiguation. Generic triggers increase the chance of accidental activation across many unrelated conversations, which can lead to privilege overreach in workflow selection or noisy, unsafe automation behavior.
The skill enables implicit invocation while providing only a broad, generic description and default prompt, which makes it easier for the platform to auto-select this skill in situations beyond a narrowly intended scope. That increases the risk of unintended activation and execution of GitHub-style workflows or developer actions in contexts where the user did not clearly request them.
The activation examples are ambiguous, truncated, and fail to define clear boundaries for when the skill should run. In an agent ecosystem, unclear scope can lead to accidental invocation on common conversational text, producing misrouting, overreach into unrelated tasks, and increased exposure to adversarial prompt content embedded in user requests.
The example trigger phrases use broad natural language that mirrors ordinary user requests and do not define clear invocation boundaries. This reinforces overbroad routing behavior by teaching the system that vague requests are sufficient to activate the skill, increasing false positives and reducing predictability.
No suspicious patterns detected.
