Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only workflow helper with broad auto-invocation wording, but no executable code, credential handling, persistence, or hidden high-impact behavior.
Before installing, be aware that the skill may activate on generic productivity or implementation requests because of broad keywords and implicit invocation. It appears safe from a security standpoint, but users who want tighter routing should prefer explicit invocation or narrower trigger wording.
The trigger phrases are generic and overlap with common user requests such as 'help me', 'I need a practical workflow', and broad terms like 'task' or 'transform'. This can cause the skill to activate in unintended contexts, leading to prompt/skill hijacking, misrouting of user requests, or accidental invocation of instructions the user did not intend to use.
The trigger phrases are broad enough to match many ordinary productivity or implementation requests, which can cause the skill to activate outside the author's intended scope. In an agent ecosystem, overbroad routing increases the chance of prompt/context hijacking, unintended tool use, or the wrong workflow being applied to unrelated user tasks.
The description says to use the skill when a user asks for broad concepts like 'work-productivity', 'proactive', 'task', or any 'practical workflow, artifact, checklist, analysis, or implementation support'. These catch-all conditions are ambiguous and can match a large fraction of normal requests, making unintended invocation and prompt-scope takeover more likely.
The trigger list includes very generic terms such as 'task', 'needs', and 'partners', which can cause the skill to activate for many unrelated user requests. Over-broad activation increases the chance that this skill intercepts prompts outside its intended scope, leading to incorrect workflow insertion, prompt-routing confusion, or unintended influence over downstream agent behavior.
The skill description defines activation conditions in very broad terms, covering general categories like work-productivity, proactive, transform, task, and requests for practical workflows or artifacts. Because the boundaries are unclear, the skill may be selected for many loosely related prompts, which weakens routing precision and can cause inappropriate handling of user requests by a mismatched agent workflow.
The trigger list includes very broad everyday terms such as 'task', 'needs', and 'partners', which can match many unrelated user requests and cause unintended skill activation. In an agent system, over-triggering can route benign conversations into this skill unexpectedly, producing irrelevant workflow actions, confusing users, and increasing the chance that the wrong automation or guidance is applied.
The trigger sentences are broad, generic, and partially malformed, making them likely to match ordinary user requests that were not intended for this skill. In an agent-routing context, this can cause inappropriate activation, prompt hijacking of normal workflows, or accidental delegation to a skill with different assumptions than the user's actual task.
A Chinese-language README contains substantial English descriptive text for core user-facing instructions and context. This can impose a language preference without explicit user opt-in or explanation, which is a natural-language locale policy concern.
The manifest allows implicit invocation while describing the skill with very broad triggers such as work-productivity, proactive, transform, task, and generic workflow help. This can cause the agent to auto-select the skill in contexts the user did not clearly intend, increasing the chance of unauthorized action, overbroad assistance, or prompt-routing to an unsuitable skill.
