Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad triggers, but it does not request sensitive access, run code, or persist changes.
Install only if you want a broad workflow helper for multi-search-engine-style productivity tasks. Because implicit invocation and generic keywords are present, prefer explicit invocation when you need it and watch for accidental activation on ordinary search-related prompts.
The trigger keywords and sample invocations are overly generic (for example, common words like 'multi', 'search', and 'engine'), which can cause the skill to activate in contexts far beyond the intended workflow. This creates a prompt-routing and unintended-execution risk: users may invoke this skill accidentally, causing irrelevant instructions or artifacts to be injected into unrelated tasks.
The trigger list includes extremely generic terms like 'multi', 'search', 'engine', 'global', and 'supports', which are common in unrelated user requests. This creates over-broad activation boundaries, increasing the chance the skill is invoked in contexts it was not designed for, potentially hijacking routing and causing unsafe or misleading assistance in unrelated tasks.
The trigger sentence is phrased so broadly that ordinary user language like asking for a 'practical workflow' or mentioning common terms such as 'multi', 'search', or 'engine' could activate the skill outside its intended niche. Overbroad activation can route unrelated conversations into this workflow, causing misfires, irrelevant instructions, or accidental execution of a skill in contexts where it was not requested.
The trigger phrases are extremely broad and include generic terms like "multi", "search", and "engine," which can cause the skill to activate in contexts unrelated to the intended workflow. In an agent system, overbroad activation increases the chance of unintended instruction injection into unrelated tasks, misrouting user requests, and applying the wrong workflow in ways that degrade safety and reliability.
The file identifies separate English and Simplified Chinese documentation variants, and this file itself is a Chinese-locale README, but it does not state whether language selection is optional or user-driven. That can create a locale-policy concern if the skill defaults users into a specific language without explicit opt-in.
The description says to use the skill when a user asks for broad categories like 'work-productivity', 'multi', 'search', or 'engine', without clear decision boundaries. Ambiguous activation guidance can cause accidental invocation and confusion about when the skill should handle a request, reducing predictability and increasing the chance of inappropriate task capture.
The skill description defines applicability in very broad terms, covering generic productivity and implementation support requests without clear boundaries. This makes the skill eligible in ambiguous contexts, which can lead to misrouting, confusing outputs, and possible overshadowing of more specialized skills that should handle the request.
The trigger list includes very broad everyday terms such as “multi”, “search”, and “engine”, which can cause the skill to activate for many unrelated user requests. Over-broad activation increases the chance of unintended routing, causing irrelevant instructions to be injected into conversations and potentially interfering with safer or more appropriate skills.
The default prompt uses broad, common-language terms such as 'help me' and references a wide category of user needs, which can cause the skill to be invoked in contexts beyond the author's intended scope. Because implicit invocation is enabled, this increases the chance of accidental routing, prompt hijacking via keyword overlap, or unexpected use of the skill in unrelated conversations.
The invocation guidance lacks clear boundaries on when the skill should and should not activate, and the listed keywords include highly generic terms that appear in many benign conversations. In an agent environment, this ambiguity increases the chance of unintended tool selection, which can degrade reliability and create unsafe workflow transitions if the wrong skill is invoked automatically.
The file advertises both English and Chinese instruction and guide files, but does not explain how the skill chooses between languages or whether the user can opt in to a locale. For multilingual skills, missing language-selection guidance can create an implicit locale policy issue if the skill defaults unexpectedly.
