Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad activation wording but no code execution, hidden data access, persistence, or destructive behavior.
Before installing, consider narrowing or explicitly invoking this skill because its generic PDF/edit/workflow keywords and implicit invocation may make it appear in unrelated conversations. The reviewed package does not show hidden execution, persistence, credential access, or data exfiltration.
The skill description uses very broad activation terms such as 'work-productivity', 'nano', 'pdf', and 'edit', which can match many unrelated user requests. This increases the chance of accidental invocation, causing the agent to apply this workflow in contexts it was not designed for and potentially overriding more appropriate or safer skills.
The keyword list contains highly ambiguous terms including 'nano', 'pdf', 'edit', 'natural', and 'language', all of which are common in ordinary conversation and many unrelated tasks. In a skill-routing system, this can lead to over-triggering and misrouting, which is dangerous because the wrong skill may shape outputs, suppress better-matched guidance, or introduce unintended workflow assumptions.
The trigger sentences and keywords are broad enough to match common terms like "work-productivity," "pdf," "nano," and generic requests for a "practical workflow," which can cause the skill to activate outside its intended scope. In an agent system, this increases prompt-routing ambiguity and can lead to unintended invocation, context confusion, or accidental application of this skill to unrelated user tasks.
The keyword list includes very broad terms like 'work-productivity', 'nano', 'pdf', 'edit', 'natural', and 'language', which are common across many unrelated tasks. This makes the skill's activation boundary unclear and raises the risk of unintended invocation, especially in shared agent environments where routing may depend on keyword matching rather than strict intent classification.
The trigger sentences are highly generic request phrasings such as 'Help me...' and 'I need a practical workflow...', which overlap with normal user language and can cause the skill to activate unintentionally. In an agent ecosystem, overly broad activation increases the chance that this skill intercepts unrelated requests, leading to misrouting, unexpected behavior, or accidental execution of instructions the user did not intend for this skill.
The trigger phrases are broad enough to match ordinary requests about PDFs, editing, or generic workflow help, which can cause the skill to activate when the user did not intend to invoke it. In an agent ecosystem, this increases the chance of incorrect tool routing, unintended prompt injection surface expansion, and execution of the wrong workflow on user content.
The example trigger sentences use broad everyday phrasing like 'Help me' and 'I need a practical workflow', which do not establish clear activation boundaries. These examples can train maintainers or downstream systems to treat ordinary requests as matches, increasing accidental activation and reducing routing precision.
The trigger list includes very generic terms such as "nano", "pdf", "edit", "natural", "language", and "instructions", which can match many unrelated user requests and cause the skill to activate outside its intended scope. Over-broad activation increases the chance of prompt-routing mistakes, unintended instruction injection from unrelated contexts, and user confusion about which skill is handling the task.
The default prompt contains broad, common-language trigger terms such as 'help me' and generic productivity-related wording, while the policy also allows implicit invocation. This increases the chance the skill is auto-selected in unrelated conversations, causing unintended execution, prompt-scope expansion, or interference with the user's intended tool flow.
This file is labeled as a Chinese README, but multiple core sections and trigger examples remain in English, which can impose a language expectation without clearly giving the user a choice. The content does not state that users may select their preferred language or that bilingual content is intentional.
