Security audit
Security checks for vulnerabilities and agentic risk
This is a text-only workflow helper with overly broad activation wording, but it does not request sensitive access, run code, install software, persist state, or hide unrelated behavior.
Install only if you want a broad workflow helper for ontology-style productivity and skill-authoring tasks. Be aware it may trigger too easily because of generic keywords and implicit invocation; prefer invoking it explicitly by name when you need it.
The skill description is extremely broad, combining many generic domains and task types such as workflow, checklist, analysis, and implementation support. This can cause the skill to activate for loosely related requests, increasing the chance of inappropriate routing, policy bypass through mis-scoping, or unexpected behavior in agent orchestration.
The keyword list includes highly generic terms like 'typed', 'knowledge', 'graph', 'structured', 'creating', and 'bug fix', which are common across many unrelated tasks. In an agent environment, such broad triggers can lead to accidental invocation, context hijacking, or the wrong skill handling sensitive requests, reducing reliability and potentially exposing users to unsafe or irrelevant outputs.
The trigger list is excessively broad and includes generic terms such as "knowledge", "graph", "structured", "creating", and "bug fix", which are common in unrelated user requests. This can cause accidental skill invocation and route ordinary conversations into this workflow without clear user intent, increasing the chance of inappropriate context capture, confusing outputs, or policy bypass through unintended activation.
The trigger sentence begins with a very broad everyday phrase ('Help me'), which can cause the skill to activate for many unrelated user requests. In an agent setting, overscoped triggers increase the chance of unintended invocation, prompt-routing errors, and accidental use of this skill in contexts where its assumptions or workflows do not fit.
The trigger phrases are broad, natural-language prompts that can plausibly match ordinary user requests rather than a narrowly scoped invocation. In an agent ecosystem, this can cause unintended auto-activation of the skill, leading to prompt hijacking of unrelated tasks, confused task routing, or unnecessary exposure of the skill's instructions in contexts where the user did not explicitly request it.
The trigger phrases are broad, generic help requests that can match ordinary conversation rather than a clearly scoped invocation. This can cause unintended skill activation, leading the agent to apply this workflow in contexts the user did not intend, which may distort outputs or interfere with safer/more appropriate skills.
The file is labeled as a Chinese README, but the concrete trigger examples users are expected to use are written only in English. This creates a locale-policy issue because the skill's operational instructions force a specific language without offering a documented alternative or opt-in.
The example triggers use vague phrasing like 'Help me' and 'I need a practical workflow' without meaningful scoping constraints, reinforcing overbroad activation behavior. This makes it more likely that downstream systems or authors will copy unsafe invocation patterns, causing misrouting and unreliable skill selection.
The invocation description says to use the skill when a user asks for broad categories like work-productivity, ontology, typed, knowledge, or graph, or whenever they need practical workflow or analysis support. These activation conditions are ambiguous and expansive, making it likely that many normal requests will match even when this skill is not the best or intended tool, leading to over-triggering and unsafe or irrelevant routing.
The default prompt contains a very broad invocation phrase tied to generic language like 'help me' and broad productivity/ontology concepts, which can cause the skill to activate in ordinary user conversations without clear intent. Because implicit invocation is also enabled, this increases the chance of unintended routing, prompt interference, or accidental exposure of the skill in contexts where it was not requested.
This trigger sentence is ambiguous because it requests a 'practical workflow' without clearly constraining the domain, inputs, or desired artifact. Ambiguous routing cues can make the agent select this skill for loosely related productivity questions, leading to incorrect automation, irrelevant outputs, or unsafe assumptions about the user's needs.
This Chinese-language README contains core descriptive content in English, which effectively imposes a language choice inconsistent with the file's locale label. The document does not tell users that English content is intentional or provide an explicit language option.
