Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with broad activation wording but no hidden code, credential access, persistence, or unsafe execution behavior.
Installers should be aware that this skill may be selected for broad productivity or self-improvement phrasing. Review or narrow the trigger terms if precise routing matters, but the artifact itself does not show dangerous execution, persistence, credential handling, or hidden behavior.
The trigger phrases are extremely broad and overlap with common words like 'self', 'improving', and 'proactive', which can cause the skill to activate in contexts the user did not intend. In an agentic workflow, unintended activation can redirect tasks, override more appropriate skills, or inject irrelevant workflow behavior into unrelated conversations, creating reliability and safety issues.
The trigger list includes extremely generic terms such as 'self', 'improving', and 'proactive', which are common in ordinary user requests and can cause accidental activation well outside the intended scope. In an agent setting, over-broad routing can misapply this skill to unrelated tasks, increasing the chance of unsafe autonomous behavior, user confusion, or inappropriate workflow generation.
The trigger keywords include very broad everyday terms such as "self", "improving", and "proactive", which can match many unrelated user requests and cause accidental skill invocation. In an agentic workflow, overbroad activation can redirect normal conversations into this skill’s behavior, increasing the chance of irrelevant automation, user confusion, or unsafe action being taken under the wrong context.
The trigger sentences and keywords are broad enough to match common terms like "self," "improving," and "proactive," which can cause the skill to activate in contexts unrelated to the intended requirement. This increases the risk of unintended invocation, causing workflow confusion, incorrect tool selection, or misrouting user requests into an overly generic self-improvement workflow.
The trigger phrases are broad and include generic terms such as 'self', 'improving', and 'proactive', which can cause the skill to activate in unrelated conversations. In an agentic workflow, overly permissive activation increases the chance of unintended invocation, context confusion, and execution of the wrong workflow on user data or tasks.
The invocation description says to use the skill when a user asks for broad concepts like work-productivity, self, improving, or proactive, without clear limits on applicability. This creates ambiguous routing boundaries, so the skill may be selected for many benign but unrelated requests, amplifying privilege-by-confusion risks in agent orchestration and degrading safety controls.
The skill description defines activation using a wide set of loosely related terms and broad task categories like practical workflows, artifacts, checklists, analysis, or implementation support. This ambiguity makes the skill easier to invoke outside its intended scope, which can lead to inappropriate routing and unreviewed execution paths in systems that depend on metadata-driven skill selection.
The default prompt uses very broad, generic trigger phrasing such as work-productivity, self-improving, proactive, workflow, artifact, checklist, analysis, and implementation support, which increases the chance the skill will activate in contexts where the user did not explicitly intend it. Combined with allow_implicit_invocation: true, this can cause unintended routing, prompt injection surface expansion, or execution of the wrong helper in mixed-scope conversations.
The file lists English and Chinese instruction and guide files as the defined language variants, but does not state that language selection follows user preference or opt-in. This can be read as a locale/language behavior constraint without an explicit choice mechanism.
In this Chinese README, key descriptive and usage content is presented in English, including the main requirement statement and trigger examples, without stating whether the skill supports multiple languages or requires English input. This can be interpreted as an implicit language constraint without user opt-in.
