Security audit
Security checks for vulnerabilities and agentic risk
This is mostly a GitHub workflow helper, but its package is inconsistently scoped and allows broad implicit invocation around repository actions.
Review this before installing if your agent has access to private repositories or authenticated GitHub tools. Use it only for explicit GitHub issue, PR, CI, or repository-planning requests, and require confirmation before any gh/API action that labels, assigns, comments, closes, merges, or otherwise changes live repository state.
The manifest and metadata present this as a GitHub issue/PR/repository helper, but the actual skill content is repurposed into a generic demand-validation and Clawhub popularity workflow. This mismatch can cause incorrect skill routing and user trust failures, leading agents to apply the skill in unrelated contexts and produce unsafe or misleading operational guidance.
The trigger sentence is extremely broad and malformed, beginning with common phrasing like 'Help me' and then embedding a large chunk of requirement text. Broad natural-language triggers increase the chance that unrelated user requests accidentally activate the skill, causing unintended context injection or workflow execution. In a GitHub/developer-helper skill, accidental activation is more concerning because the skill may influence repository, issue, or PR handling decisions.
The trigger examples are broad, generic, and partially templated in a way that could cause the skill to activate for loosely related GitHub or software-help requests without clear user intent. In an agent setting, overbroad invocation can route sensitive repository, issue, or PR tasks into the wrong workflow, increasing the chance of unintended actions, context leakage, or unsafe automation.
The trigger phrases are broad enough to match many ordinary GitHub-related requests, which can cause the skill to activate outside the author's intended scope. In an agent environment, overbroad routing can lead to unintended execution paths, misuse of repository/issue workflows, or the agent applying this skill when a more appropriate or safer skill should handle the request.
The trigger list consists of generic terms like "GitHub," "issue," "PR," "review," and "branch," which commonly appear in ordinary development discussions. Without stronger activation constraints or negative examples, the skill could be invoked unintentionally for routine GitHub mentions.
The title and trigger framing suggest a GitHub interaction helper, but the surrounding documentation instead describes a broad workflow-planning and demand-validation skill. In an agent environment, this semantic mismatch increases the chance of inappropriate invocation, confusing downstream behavior and causing the agent to ignore task-specific safety expectations for repository operations.
The trigger keywords include broad terms like software-and-data, github, cli, issue, run, and api, which can match many unrelated user requests. Overbroad activation can cause this mis-scoped skill to preempt more appropriate skills, increasing the likelihood of irrelevant, misleading, or unsafe guidance in real workflows.
The example trigger phrases are vague, repetitive, and broad enough to overlap with ordinary help requests, while still embedding unrelated demand-validation language. This makes accidental activation more likely and reinforces the underlying scope confusion, which can degrade agent reliability and produce contextually wrong advice.
The default prompt describes activation as "inspect my GitHub context and plan the next repository action," which is broad and does not clearly constrain when this skill should be invoked versus other GitHub or planning skills. The file also enables implicit invocation, increasing the risk that ordinary repository-help requests could trigger this skill unintentionally.
This trigger remains too generic because it starts with an everyday request pattern ('I need a practical workflow for') followed by verbose requirement text rather than a precise capability name or bounded intent. That makes false activations likely in normal conversation, which can cause the agent to apply this skill when the user did not request GitHub interaction support. In this skill context, misrouting is more dangerous because it can steer development or repository operations based on irrelevant instructions.
The file list explicitly states English and Chinese instruction and README files, but the README does not explain how the user's preferred language is selected. This can be a locale-policy concern if the skill defaults to a language without offering user choice or documenting a justified locale constraint.
The file is presented as a Chinese README, but key user-facing content and trigger phrases are written in English, including the demand description and invocation examples. This creates an implicit language/locale inconsistency without offering the user a choice or explaining that English prompts are required.
No suspicious patterns detected.
