Security audit
Security checks for vulnerabilities and agentic risk
This is a Markdown-only Chinese renovation troubleshooting skill with no hidden code or system access, though users should be cautious with water and electrical repair advice.
Installers should understand this as a Chinese-language renovation advice skill. It appears safe from an agent-security perspective, but for active leaks, breaker trips, exposed wiring, burning smells, sewage backup, gas, load-bearing work, mold, or unknown hidden damage, shut off the relevant utility where safe and use a licensed professional rather than relying on DIY steps or photo-only diagnosis.
The skill covers leakage, blockage, breaker trips, and other water/electrical fault scenarios while omitting user-facing warnings about immediate hazards and emergency actions. In this context, users may follow repair-oriented advice instead of first isolating power/water or seeking urgent qualified help, increasing the chance of electrocution, flooding, mold, and property loss.
The skill explicitly pushes concrete DIY repair steps and deprioritizes deferring to qualified professionals, but it does not add guardrails for safety-critical work such as structural, waterproofing, gas, or electrical issues. Users may attempt hazardous repairs based on terse instructions and cause injury, fire, shock, leaks, or hidden damage.
The photo-based diagnosis flow encourages judging severity and recommending fixes from images alone, but photos can miss hidden moisture intrusion, unstable substrate, live electrical risks, or code violations. This can create false reassurance and lead users to choose cosmetic fixes when the underlying defect is dangerous or requires invasive inspection.
The entire skill is written only in Chinese and references a Xi'an renovation knowledge source, but it does not state that the skill is intended only for Chinese-speaking or region-specific users, nor does it offer a language choice. Under the language/locale policy, forcing a single language without user opt-in can be a policy violation.
The entire skill content is presented only in Chinese and does not indicate that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is documented and justified.
The entire skill content is written only in Chinese and provides no indication that users may choose another language or locale. Under the policy rule for natural-language constraints, forcing a specific language without opt-in can be a locale-policy issue when no justification is documented.
No suspicious patterns detected.
