Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with broad trigger wording, but it does not include code execution, credential access, persistence, or hidden data handling.
Install only if you want a general productivity workflow helper for Humanizer-style writing and reliability tasks. Be aware it may be selected for broad terms like writing, editing, reviewing, remove, or bug fix unless the platform lets you disable implicit invocation or narrow triggers.
The trigger keywords and example phrases are broad enough to match many ordinary writing, editing, and review requests, causing the skill to activate outside its intended scope. In an agent ecosystem, this can hijack routing decisions, surface irrelevant guidance, and increase the chance that users are steered into a workflow they did not request.
The trigger list includes very broad everyday terms such as 'remove', 'writing', 'text', 'editing', 'reviewing', and 'bug fix', which can match many unrelated user requests. This increases the chance the skill is invoked outside its intended scope, causing inappropriate workflow injection, user confusion, or unintended handling of content.
The trigger sentences are generic and overlap with ordinary user requests like asking for help, needing a workflow, or handling a topic. That increases the chance of accidental skill invocation or overly broad routing, which can cause the agent to apply this workflow in unintended contexts and produce misleading or irrelevant actions.
The trigger phrases are broad, generic help requests that can overlap with ordinary user language, causing the skill to activate unintentionally. In an agent ecosystem, overbroad activation can route unrelated tasks into this workflow, leading to incorrect behavior, user confusion, or unintended processing of sensitive prompts.
The sample trigger phrases are phrased as generic help requests and repeat broad demand language rather than clearly bounded activation conditions. In routing systems that learn from examples, this can expand matching behavior and make accidental activation more likely for unrelated productivity or editing tasks.
The skill metadata and default prompt use very broad terms such as 'work-productivity', 'workflow', 'analysis', and 'implementation support' while also allowing implicit invocation. This can cause the platform to select the skill for loosely related requests, increasing the chance of unintended activation and execution in contexts the user did not specifically request.
The invocation guidance mixes vague keywords and natural-language examples without defining strict activation criteria, which makes the skill easy to trigger accidentally. Because this skill is framed as a general helper for workflows, ambiguous routing can over-broaden its use and interfere with correct tool or skill selection across many unrelated tasks.
The trigger examples are broad natural-language phrases that resemble ordinary user requests, increasing the chance the skill activates outside its intended scope. In an agent environment, unintended activation can route unrelated prompts into this skill, causing workflow confusion, incorrect task handling, or policy bypass through skill misselection.
The README describes separate English and Chinese instruction files, but does not indicate how a user can choose their preferred language or whether language selection is optional. This can be a natural-language policy concern if the skill defaults to a language or locale behavior without user opt-in.
This Chinese README contains core operational description text in English, which can impose a language choice on users without any stated opt-in or alternative. The file does not indicate that users may choose their preferred language for instructions or outputs.
