Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with broad auto-invocation wording, but no hidden code, credential access, persistence, or destructive behavior was found.
Install only if you want this broad ontology/workflow planning helper available through implicit invocation. Be aware it may activate on loosely related productivity, knowledge-graph, or bug-fix requests unless your agent router is strict.
The skill description and activation scope are broad enough to match many ordinary requests about productivity, knowledge, graphs, implementation support, or analysis. In an agent environment, this can cause unintended auto-invocation or routing precedence over more specific skills, leading to inappropriate behavior, context capture, or downstream execution of the wrong workflow.
The keyword list contains highly generic terms such as 'knowledge', 'graph', 'structured', 'memory', 'creating', and 'bug fix' that are common across many unrelated tasks. This makes the skill easy to invoke accidentally and increases the chance that unrelated user requests are hijacked into this skill's workflow, degrading routing integrity and potentially exposing user context to an unintended skill path.
The trigger sentence is so broad and natural-language-like that it could match ordinary user requests that were not intended to invoke this skill. In an agent environment, overbroad activation can cause the wrong workflow to run, leading to irrelevant actions, context hijacking, or unintended handling of unrelated tasks.
The trigger sentences are broad, natural-language phrases that could match ordinary user requests and cause the skill to activate when the user did not explicitly intend to invoke it. In an agent ecosystem, unintended invocation can redirect workflows, inject unexpected instructions, or cause the wrong skill to handle sensitive work-productivity or knowledge-graph tasks.
This file is explicitly a Chinese-language README and does not indicate that language selection is optional or based on user preference. Under the policy, locale-specific presentation should offer user choice or clearly document a justified regional constraint.
The trigger phrases are broad, generic, and closely resemble ordinary user requests for help or workflows, which can cause the skill to activate outside its intended scope. In an agent ecosystem, this creates prompt-routing ambiguity and can lead to unintended invocation, irrelevant actions, or interference with more appropriate skills.
The example trigger sentences use generic phrases like 'Help me' and 'I need a practical workflow' without clearly delimiting when this skill should be selected instead of other helpers. While likely intended as usability guidance, these examples reinforce over-broad activation behavior and make ambiguous routing more likely in real deployments.
The invocation description says to use the skill when a user asks for broad categories or needs practical support, but it does not define clear inclusion or exclusion criteria. This ambiguity increases the chance of over-triggering on ordinary productivity or knowledge-related requests, which can misroute users and expand the skill's effective authority beyond what was intended.
The trigger keywords are broad and include generic terms such as "knowledge", "graph", "structured", and "creating", which are common across many unrelated requests. This can cause accidental invocation of the skill outside its intended scope, leading to prompt routing errors, inappropriate workflow application, or masking of more suitable skills.
The skill enables implicit invocation, but the trigger description is broad and generic rather than narrowly scoped to specific user intents. This can cause the agent to invoke the skill in situations the user did not clearly request, expanding the skill’s influence over workflows and increasing the risk of unintended actions, misleading guidance, or prompt-surface abuse through overbroad matching.
The invocation guidance does not define clear boundaries, required conditions, or disallowed cases, so the agent may route loosely related requests into this skill. That increases the chance of misfires and prompt-scope confusion, especially because the skill is framed broadly around workflows, analysis, implementation support, and adjacent tasks.
The file explicitly defines English and Chinese instruction and guide variants, but it does not say how the user's preferred language is selected or whether the user can choose. That can create a locale-policy concern if the skill defaults to a language without user opt-in.
