Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-style workflow helper with no executable payload, though its auto-activation wording is overly broad and may trigger in unrelated productivity requests.
This skill is reasonable to install if you want a lightweight workflow/checklist helper, but review its broad implicit triggers because it may appear for generic task or bug-fix requests where a more specific skill would be better.
The trigger phrases are broad, generic, and overlap with common requests like help, workflow, task, or bug fix, which can cause the skill to activate outside its intended scope. In an agent ecosystem, this increases the chance of unintended invocation, routing confusion, and inappropriate application of the skill’s workflow to unrelated user requests.
The manifest description says to use the skill when a user asks for broad concepts such as 'work-productivity', 'proactive', 'task', or practical support, which are common across many benign conversations. This ambiguous invocation language can cause unintended auto-selection of the skill, reducing routing precision and potentially exposing users to irrelevant instructions or outputs from the wrong capability.
The trigger keywords are extremely broad and include common terms like 'task', 'needs', and 'proactive', which can cause the skill to activate for many unrelated user requests. Overbroad activation increases the chance this skill intercepts conversations it was not intended to handle, leading to misrouting, prompt-surface expansion, and unsafe or confusing behavior in multi-skill environments.
The description says to use the skill when a user asks for broad categories like 'work-productivity', 'proactive', 'transform', or 'task', which are ambiguous and apply to many benign conversations. This creates an activation-scope vulnerability where the skill may be selected outside its intended niche, increasing misrouting and unexpected behavior across the agent system.
The trigger list includes very common words such as 'task', 'needs', and 'partners', which can cause the skill to activate for many unrelated requests. Overbroad activation increases the chance that the agent invokes this workflow in the wrong context, potentially overriding more appropriate skills or causing unintended processing of user requests.
The trigger phrases are broad enough to match common work/productivity requests and generic terms like "task," "proactive," or "needs," which can cause unintended activation of the skill. In an agent ecosystem, this can route unrelated user requests into this workflow, creating mis-execution, confusing outputs, or bypass of the more appropriate skill-selection path.
This file is explicitly a Chinese-language README and presents the skill instructions and usage entirely in Chinese, without any user-facing language-choice guidance inside the document. For locale policy review, this can be read as enforcing a specific language presentation unless the user separately discovers another language variant.
The trigger section provides only broad keywords and positive examples, but no constraints or negative examples showing when the skill should not run. Without specificity, the skill is more likely to activate on vague everyday language, increasing accidental invocation and weakening safety boundaries between skills.
The manifest description and default prompt use very broad, generic activation language such as helping with 'work-productivity', 'proactive', 'task', 'analysis', or 'implementation support' without defining concrete boundaries or trigger conditions. This increases the chance the skill will be invoked in unrelated contexts, causing overreach, unexpected prompt injection surface expansion, and accidental handling of requests outside its intended safety model.
Enabling implicit invocation without tight scope controls allows the platform to auto-select this skill based on loose semantic matches rather than deliberate user choice. In combination with the broad manifest language, this can cause unintended activation in many conversations, exposing users to unreviewed behavior and increasing the chance of unsafe or irrelevant assistance being inserted into workflows.
The keyword list includes very common terms like 'task', 'transform', 'partners', and 'needs', which are likely to match a wide range of benign user prompts. In a skill-routing system, this creates trigger ambiguity and over-capture, making the agent invoke this skill outside its intended scope and potentially produce irrelevant or unsafe workflow guidance.
The trigger sentences are so generic that they can activate this skill for ordinary productivity requests unrelated to the intended requirement. Overbroad routing increases the chance of unintended skill invocation, which can cause mis-scoping, incorrect automation choices, and policy bypass through inappropriate tool selection or workflow execution.
The README specifies English and Chinese instruction files, but does not state how language is selected or whether the user can choose their preferred locale. This can create a language/locale policy concern if the skill defaults to one language without explicit user opt-in.
