Security audit
Security checks for vulnerabilities and agentic risk
This is a style/persona skill for Network Spirituality art writing with no executable code or system access, though its activation wording is somewhat broad.
Install this only if you want the agent to use a specific Network Spirituality/Remilia-style voice for creative or aesthetic tasks. Be aware that its trigger wording is broad, so it may color some general art or digital-aesthetic writing unless invocation is controlled by the host.
The description is broad enough to trigger on generic creative-writing or aesthetics requests, which can cause the skill to activate outside its intended niche. Over-broad activation increases the chance that unrelated user tasks are steered into this persona, reducing user control and making downstream prompt interference more likely.
The 'When to Use' section uses high-level categories like creating art descriptions, writing in a voice, and describing digital spaces, which are common requests across many benign contexts. This ambiguity can cause unnecessary or incorrect invocation, letting the skill shape outputs in ways the user did not request.
The guidance says to 'Use bilingual elements (English/Chinese) when appropriate,' which can impose a language or locale choice without asking the user. Under the policy, forcing or steering output toward a specific language is a violation unless the user is given a choice or the constraint is clearly justified.
No suspicious patterns detected.
