Security audit
Security checks for vulnerabilities and agentic risk
This skill is a document-only workflow helper with overly broad activation wording but no hidden execution, persistence, credential access, or destructive behavior.
This is reasonable to install if you want a general helper for agent workflow planning and reliability work. Consider tightening or disabling implicit invocation if you do not want ordinary requests containing broad words like self, improving, proactive, learning, organizing, or bug fix to route through this skill.
The manifest says to use the skill when a user asks for broad concepts like "work-productivity," "self," "improving," or "proactive," which creates an overly permissive invocation boundary. This can make the skill match many unrelated conversations, causing accidental selection and increasing the risk of misapplication, instruction collision, and degraded agent behavior.
The trigger list includes extremely generic terms such as "self," "improving," and "proactive," which are common in ordinary user requests and can cause the skill to activate far outside its intended scope. In an agent environment, this increases the chance of unintended routing, prompt-scope capture, and interference with more appropriate skills, reducing reliability and potentially exposing users to irrelevant or unsafe workflow guidance.
The trigger list is overly broad and includes generic words like 'self', 'improving', and 'proactive', which are common in normal conversations. This can cause accidental skill activation outside its intended scope, leading the agent to apply the wrong workflow, generate irrelevant actions, or override more appropriate skills in multi-skill environments.
The trigger examples use very common phrases like 'Help me' and 'I need a practical workflow' tied to a broad requirement description, which can cause the skill to activate for many unrelated requests. In an agent system, over-broad invocation increases the chance of the wrong workflow handling user input, leading to irrelevant actions, confusion, or unsafe automation being applied outside its intended scope.
The trigger sentence is generic enough to match ordinary user requests for 'help' and 'practical help' without strong scoping, which can cause the skill to activate outside its intended domain. In an agent ecosystem, overly broad activation increases the chance of prompt hijacking, incorrect routing, or unintended execution of a workflow that may influence subsequent decisions or outputs.
This activation phrase uses broad language like 'I need a practical workflow' that could apply to many unrelated requests, making accidental or adversarial invocation more likely. Because the skill is positioned as proactive and self-improving, misactivation can be more dangerous than a passive informational skill since it may steer planning, recommendations, or workflow generation in contexts the user did not intend.
The documented trigger phrases are broad, generic, and overlap with common user language such as 'self', 'improving', and 'proactive', which can cause unintended activation of the skill outside the author's intended context. In an agent ecosystem, accidental invocation can route unrelated tasks through this skill, creating confusion, inappropriate behavior chaining, and increased risk when the skill performs proactive or self-improving workflow actions.
The activation condition in the description is vague and mixes broad thematic categories with loosely defined user needs. In practice, this ambiguity increases the chance of inappropriate invocation, especially because the skill already covers a wide range of outputs such as workflows, checklists, analyses, and implementation support.
The default prompt is written as a very broad natural-language invocation phrase and the policy allows implicit invocation, which increases the chance the skill will activate in ordinary user conversations without clear user intent. In a self-improving/proactive workflow context, unintended activation can cause the agent to steer tasks, generate artifacts, or influence workflows unexpectedly, creating prompt-scope confusion and possible misuse of downstream capabilities.
The trigger section provides keywords and positive examples but no boundary conditions, exclusions, or negative examples, so the routing logic has no clear way to distinguish intended use from ordinary productivity requests. This ambiguity can systematically misroute prompts to the skill, which is especially risky for proactive or self-improving workflows that may propose autonomous planning or changes beyond what the user intended.
This file is presented as a Chinese README, but key user-facing descriptive content is written in English, which can impose an implicit language constraint on users without opt-in or explanation. That may violate language/locale policy expectations when no user choice or rationale is provided.
