Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overbroad activation wording but no executable code, credential handling, persistence, or hidden data movement.
Install only if you want a general PollyReach-style workflow helper. Be aware it may be invoked too often because its trigger words are generic; prefer explicit invocation by skill name and review any suggested code or workflow changes before applying them.
The trigger examples and keywords are broad enough to match common, unrelated user requests, increasing the chance this skill is invoked outside its intended scope. In an agent ecosystem, over-broad activation can cause unintended workflow execution, misrouting, or inappropriate handling of user tasks, especially because terms like 'every', 'phone', 'number', and 'things' are generic.
The trigger phrases are extremely broad and include common words such as 'every', 'phone', 'number', 'ability', and 'things', which can cause the skill to activate for unrelated user requests. In an agent environment, overbroad activation can route arbitrary tasks into this workflow, increasing the chance of unintended actions, incorrect tool use, or prompt-surface expansion beyond the user's intent.
The description says to use the skill when a user asks for broad terms like work-productivity or needs a practical workflow, artifact, checklist, analysis, or implementation support, which describes an extremely wide range of normal requests. This vague activation condition can cause the skill to intercept many unrelated tasks, leading to misapplication, prompt-routing errors, and reduced trust in the agent’s behavior.
The trigger keyword list includes very generic words such as "every," "phone," "number," "ability," "things," and "done," which can cause the skill to activate for unrelated user requests. Over-broad activation increases the chance of unintended routing, causing the agent to apply this skill in contexts where its workflow, assumptions, or outputs are inappropriate.
The trigger keyword list includes generic everyday words like "every", "phone", "number", "ability", "things", and "done", which creates a high risk of unintended skill invocation during unrelated conversations. Over-broad activation can route users into the wrong workflow, causing context confusion, unsafe automation suggestions in the wrong setting, and making prompt-routing behavior easier to manipulate.
The file lists separate English and Chinese instruction and guide files, but the README does not describe how the user's preferred language is selected or whether language choice is optional. This can create a locale-policy issue if the skill defaults to a language without explicit user opt-in.
A file presented as a Chinese-language README contains core instructional and descriptive content in English, including the requirement description and target-user text. This can impose an unannounced language expectation on users instead of clearly offering language selection or justifying the mixed-locale behavior.
The example trigger sentences are generic and effectively mirror normal help requests without strong domain anchors, reinforcing over-selection of the skill. In systems that learn or match from examples, this can bias routing toward this skill for many ordinary productivity or workflow questions.
The invocation description says to use the skill when users ask for broad categories like work-productivity or practical workflow support, which is too ambiguous for safe routing. This increases the chance that unrelated requests get captured by the skill, leading to misapplication of instructions and unreliable or unsafe outputs in contexts the skill was not designed for.
The sample trigger phrases are written like ordinary user requests rather than precise activation examples, which encourages accidental invocation and weakens routing boundaries. Because they are broad and naturalistic, they normalize activation on partial topic overlap instead of explicit user intent, increasing misfires and prompt-selection errors.
The default prompt includes a very broad, natural-language trigger phrase tied to common productivity terms, which increases the chance of accidental or overly broad invocation. Combined with implicit invocation being enabled in this skill, the agent may activate in contexts the user did not clearly intend, causing prompt-scope confusion, unintended actions, or unsafe blending with unrelated requests.
The trigger guidance does not clearly define when the skill should and should not activate, and the sample triggers are truncated and vague. Ambiguous activation boundaries can cause overbroad routing, where unrelated user inputs are matched to this skill, creating reliability and safety issues because the skill may produce workflows or artifacts outside its validated domain.
The trigger examples include broad, everyday terms such as "phone" and generic help phrasing that are not tightly bound to the skill's actual scope. In an agent routing system, this can cause accidental activation on unrelated requests, leading the skill to handle prompts it was not intended for and increasing the chance of unsafe or low-quality task execution.
No suspicious patterns detected.
