Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad activation wording, but it does not request sensitive access, persistence, or executable authority.
Install only if you want a general Nano PDF-style workflow helper. Be aware it may activate on broad PDF or editing language unless the platform requires explicit invocation, so prefer calling it by name when you actually need it.
The manifest description says to use the skill when a user asks for broad terms like 'work-productivity', 'nano', 'pdf', or 'edit', which creates an overly permissive invocation boundary. Because manifest descriptions often guide automatic selection, this can cause the skill to be chosen for unrelated tasks, degrading safety and correctness by misrouting user requests.
The trigger keyword list is excessively broad and includes generic terms such as 'nano', 'pdf', 'edit', 'natural', and 'language', which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance that the agent applies the wrong workflow or exposes users to unintended instructions, especially in multi-skill environments where trigger collisions affect routing reliability and safety.
The trigger list includes very common terms such as "nano", "pdf", "edit", "natural", and "language", which can match many unrelated user requests and cause the skill to be invoked unexpectedly. Over-broad invocation increases prompt-scope confusion and can route users into an unintended workflow, raising the chance of unsafe or irrelevant actions being suggested under the wrong context.
The trigger sentence is phrased broadly enough that ordinary user language about getting help or needing a workflow could accidentally activate this skill outside its intended context. In an agent ecosystem, unintended invocation can route tasks to the wrong skill, causing inappropriate handling of user data, incorrect outputs, or bypass of more specific safeguards.
The invocation guidance lacks clear boundaries on when the skill should and should not activate, making the trigger scope ambiguous. Because the skill covers broad concepts like productivity, PDFs, editing, and implementation support, an agent may over-match many unrelated user requests, leading to unintended skill selection and unreliable or unsafe task handling.
The trigger sentence is broad and natural-language-like, which increases the chance the skill is invoked during ordinary conversation rather than only when explicitly intended. In an agent ecosystem, unintended invocation can cause incorrect workflow routing, surprise behavior, or execution of the wrong instructions, especially because the skill targets generic terms like 'help me' and common productivity topics.
The trigger phrases are very broad and include common terms like "nano", "pdf", "edit", and generic requests for a "practical workflow," which can cause the skill to activate in many unrelated conversations. This increases the chance of unintended invocation, prompt hijacking of user intent, and confusing or inappropriate workflow insertion in benign tasks.
The example trigger phrases are vague and mostly restate the broad requirement text rather than defining precise activation conditions. Ambiguous examples reinforce loose matching behavior, making accidental invocation more likely and reducing operator understanding of when the skill should or should not run.
The description says to use the skill when users ask for broad categories like work-productivity, nano, pdf, edit, or practical workflow support, but it does not define clear boundaries for when the skill should not apply. This ambiguity can cause accidental selection of the skill for unrelated requests, reducing reliability and potentially exposing users to mismatched guidance.
The default prompt contains broad, common-language trigger terms such as 'help me' and generic productivity wording, which can cause the skill to be invoked in many unrelated conversations. Because implicit invocation is enabled, this increases the chance of accidental routing, unexpected prompt injection surface expansion, and user confusion about which skill is acting.
This trigger is ambiguous and underspecified, so the agent may invoke the skill for loosely related requests that mention practical workflows or hardening without actually intending Nano PDF-style assistance. That increases the risk of misrouting, confusion, and accidental execution of the wrong workflow in contexts where different controls or expertise are required.
The file presents itself as the Chinese user guide and references Chinese-language documentation variants, but it does not state that language is optional or user-selectable. Under the policy, locale-specific behavior should either be opt-in or clearly justified as region-specific.
No suspicious patterns detected.
