Security audit
Security checks for vulnerabilities and agentic risk
This skill is a low-risk workflow helper, though its activation wording is too broad and may trigger in unrelated PDF or editing requests.
Before installing, be aware that this skill may activate for generic PDF, edit, or workflow requests where it is not the best fit. It appears safe as a guidance-only package, but the publisher should narrow triggers to explicit Nano PDF workflow requests and clean up the mixed-language documentation.
The trigger phrases are broad and include generic terms like "nano", "pdf", "edit", and "natural language instructions", which can cause the skill to activate in unrelated contexts. In an agent ecosystem, unintended invocation can route user requests into the wrong workflow, causing incorrect actions, confused delegation, or unsafe processing of documents the user did not intend this skill to handle.
The skill description says to use the skill whenever a user asks for broad terms like work-productivity, nano, pdf, edit, workflow, artifact, checklist, analysis, or implementation support. These are common terms that can match many unrelated requests, causing accidental activation and inappropriate context injection into conversations. In an agent ecosystem, overbroad routing can degrade reliability and may steer users into actions or templates that do not fit their actual intent.
The keyword list includes highly generic triggers such as nano, pdf, edit, natural, language, and instructions without qualifiers. These tokens are common in ordinary user messages, so the skill may activate far outside its intended domain, increasing the chance of prompt-routing errors, irrelevant automation, or unsafe application of advice to the wrong task. Because trigger matching is often automated, generic keywords materially raise the probability of unintended invocation.
The trigger keyword list includes very broad everyday terms such as "nano", "pdf", "edit", "natural", "language", and "instructions", which can match many unrelated user requests. This can cause the skill to activate outside its intended scope, injecting irrelevant workflow guidance into unrelated conversations and increasing the chance of unsafe or confusing agent behavior.
The trigger phrases are extremely broad and include common terms like "pdf," "edit," and generic requests for a "practical workflow," which can cause the skill to activate for unrelated user intents. Overbroad routing increases the chance of unintended invocation, confusing behavior, and accidental use of this skill in contexts where its assumptions or outputs do not fit the user's request.
The trigger phrases are broad, repetitive, and include generic terms like 'help me', 'practical workflow', 'nano', 'pdf', and 'edit', which can cause the skill to be invoked in contexts beyond its intended scope. In an agent environment, overbroad activation can route unrelated user requests into this skill, producing inappropriate guidance or interfering with safer, more specific skills.
This file is presented as a Chinese README, but key user-facing instructional content is written in English, which can impose a language expectation without opt-in. The document does not state that English is required, optional, or user-selectable, so the locale behavior is not clearly justified or configurable.
The example trigger sentences reinforce ambiguous activation by repeating broad marketing-style language instead of concrete, bounded intents. They do not show what should and should not invoke the skill, so implementers may configure routing too loosely and users may be matched to this skill for loosely related productivity or PDF requests. This increases misrouting risk and weakens operator understanding of the skill's safe scope.
The description says to use the skill whenever a user asks for broad topics like work-productivity, nano, pdf, or edit, or whenever they need a practical workflow or checklist around the requirement. This activation boundary is so broad that the skill may be selected for many unrelated tasks, leading to misrouting, prompt interference, and unreliable agent behavior.
The example trigger phrases are vague and repetitive, and they do not distinguish valid invocations from ordinary conversation. Poor examples increase the chance that developers or routing systems generalize too broadly, compounding accidental activation and reducing predictability.
The default prompt includes the generic trigger phrase 'help me', which is so broad that the skill may be invoked in many unrelated user requests. Combined with allow_implicit_invocation: true, this increases the chance of unintentional activation, causing the agent to inject this skill's behavior or instructions into contexts where the user did not specifically request it.
No suspicious patterns detected.
