Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad activation wording but no executable code, credential access, persistence, or hidden behavior.
Install only if you want a general workflow helper for proactive-agent-style productivity tasks. Be aware that its trigger wording is broad, so it may appear for ordinary task or bug-fix requests where a more specific skill would be better.
The trigger phrases are generic enough to match ordinary requests about workflows, tasks, bug fixes, or proactive help, which can cause the skill to activate outside its intended scope. In an agent ecosystem, over-broad routing can misdirect user requests, unexpectedly inject this skill's behavior into unrelated tasks, and undermine user intent or policy boundaries.
The skill description includes broad trigger concepts such as 'work-productivity', 'proactive', 'transform', and 'task', which are common in many unrelated user requests. This can cause the skill to activate outside its intended scope, leading to prompt hijacking of routing, irrelevant assistance, or accidental exposure of internal workflow behavior in contexts where the skill should not run.
The keyword list contains highly generic words such as 'proactive', 'transform', 'task', 'needs', and 'bug fix', any of which may appear in ordinary conversations. In a skill-routing system, such vague triggers can cause frequent unintended invocation, crowd out more appropriate skills, and widen the attack surface by making it easier for adversarial or accidental prompts to activate this skill.
The trigger list is overly broad and includes common terms like 'task', 'proactive', 'needs', and 'bug fix', which can cause the skill to activate in many unrelated conversations. In an agent system, unintended invocation can override user intent, inject irrelevant workflow behavior, or steer handling toward this skill when a more appropriate or safer skill should respond.
The trigger sentences and keywords are broad enough to match many ordinary productivity requests, which can cause the skill to activate outside its intended scope. In an agent ecosystem, this kind of overmatching can misroute user tasks, override more appropriate skills, and increase the chance that users receive irrelevant or unsafe automation guidance without explicitly opting into this workflow.
This README is entirely in Chinese and presents the skill in that locale without any user-choice mechanism, which can cause the system to route or present the skill in a language the user did not request. While not directly a code-execution risk, it can degrade user understanding, obscure behavior, and increase the likelihood of accidental or inappropriate use.
The trigger phrases are broad and include generic terms like "task," "needs," and "bug fix," which are common in ordinary user requests. This can cause the skill to activate unintentionally, leading to prompt hijacking of unrelated conversations and increasing the chance that users receive this workflow when they did not request it.
The description defines activation using a wide range of generic requests such as needing a practical workflow, checklist, analysis, or implementation support for broad productivity themes. This weak scoping increases the chance that the skill is selected outside its intended niche, potentially causing misrouting, unnecessary instruction injection, and reduced reliability of agent behavior.
The manifest allows implicit invocation while providing very broad, generic activation text tied to common productivity terms and a vague default prompt. This increases the chance the skill is auto-selected in unintended contexts, causing overbroad delegation, prompt-surface expansion, and unexpected execution of skill behavior without clear user intent.
The file lists English and Chinese documentation variants, but does not state how language selection is determined or that the user can choose their preferred locale. While not a strong violation, the natural-language documentation setup may imply locale handling without explicit opt-in or justification.
The file includes user-facing trigger phrases only in English while also embedding Chinese-language source titles in the evidence section, but it does not state whether the skill supports multiple languages or requires English invocation. This can create an implicit language expectation without documenting user choice or a justified locale constraint.
