Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad auto-invocation wording, but no hidden code, persistence, credential access, or destructive behavior.
This skill is reasonable to install if you want a general workflow helper for proactive-agent style planning. Be aware that its trigger wording is broad and implicit invocation is enabled, so it may activate for generic productivity or task requests more often than expected.
The trigger examples are so broad and generic that they can match ordinary user requests unrelated to this skill's intended scope, causing the skill to activate unexpectedly. In an agent setting, overbroad invocation can route benign tasks through specialized workflow logic, increasing the chance of inappropriate actions, confusion, or unsafe automation chains.
The description says to use the skill whenever a user asks for broad categories like work-productivity, proactive, transform, task, or practical workflow support, which makes the activation boundary ambiguous. In agent systems, overly broad routing can hijack unrelated requests, introduce irrelevant instructions, and reduce user control over which skill is applied.
The trigger list includes very generic terms such as "task", "transform", "needs", and "proactive", which are likely to appear in normal user conversations unrelated to this skill. That can cause unintended activation and context injection, making the agent follow workflow instructions when the user did not explicitly request this capability.
The description says to use the skill whenever users mention broad concepts like work productivity, proactive behavior, transformation, tasks, or practical support, which makes invocation boundaries unclear. This ambiguity increases the likelihood that the skill will be selected outside its intended scope, leading to misrouting, confusing outputs, or unsafe automation choices in contexts where a different skill should apply.
The trigger list includes very broad, common terms such as 'task', 'needs', and 'bug fix', which can cause the skill to activate in many unrelated conversations. In an agent setting, unintended activation can steer workflows, inject irrelevant guidance, or override more appropriate skills, increasing the chance of incorrect or unsafe automation behavior.
Enabling implicit invocation while the skill definition remains broad creates a meaningful misrouting risk: the agent may auto-select this skill without clear user intent. In this context, the danger is elevated because the skill is framed as a general workflow helper, so unintended invocation could affect many unrelated prompts and lead to inappropriate actions, suggestions, or handling of sensitive work-productivity context.
The trigger sentence is broad and uses common phrasing, which can cause the skill to activate for unrelated user requests. In an agent environment, overbroad activation increases the chance of misrouting tasks, causing the wrong workflow to run and potentially producing unsafe or irrelevant actions without clear user intent.
The trigger keywords and example invocations are broad enough to match many ordinary productivity or task-related requests, which can cause unintended activation of the skill. In a proactive-agent workflow, accidental invocation can route users into the wrong workflow, causing confusing outputs, context misuse, or inappropriate actions based on misunderstood intent.
The skill metadata is excessively broad and repetitive, using generic terms like work-productivity, proactive, transform, task, workflow, artifact, checklist, analysis, and implementation support. This increases the chance the platform will invoke the skill for loosely related requests, causing unintended routing, over-collection of user context, or execution in situations the user did not clearly request.
This trigger remains generic and underspecified, so many ordinary productivity or workflow requests could match even when the user did not intend to invoke this skill. Such ambiguity is risky in assistant orchestration because it expands the skill's authority surface and can lead to inappropriate handling of requests, reducing reliability and possibly bypassing more suitable controls.
The user-facing README includes Chinese-language evidence titles alongside English content, but it does not explain any language or locale expectations for users. This can create an implicit language inconsistency without an explicit opt-in or justification.
This file presents the skill documentation entirely in Chinese while still containing English content fragments, and it does not state that the skill is region-specific or offer language/locale choice. That can violate language/locale policy expectations when users are not explicitly given an opt-in or justification for the locale constraint.
