Security audit
Security checks for vulnerabilities and agentic risk
This is a prompt-only health appointment preparation skill that organizes user-provided symptom notes and does not request code execution, network access, credentials, or persistence.
Install only if you are comfortable entering health details into your AI assistant for appointment preparation. Review outputs for accuracy before sharing with a clinician, and use emergency or crisis services for severe, sudden, dangerous, or rapidly worsening symptoms.
Line L205 states the skill must produce "English-only prompt-flow content," which is a language-policy restriction expressed in natural language. The file does not offer the user a language choice or explain a justified region-specific need for English-only output.
The acceptance criteria state "Skill is English-only," which is a natural-language locale restriction. Under the policy, forcing a specific language without user opt-in can be a violation unless the constraint is justified as region-specific or the user is offered a choice.
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
Before routine logging, ask whether any urgent red flags are present. Keep this general and safety-focused.
Advise urgent care or emergency services now if the user reports severe, sudden, or potentially life-threatening symptoms, including but not limited to:
- Chest pain, pressure, trouble breathing, fainting, or signs of stroke
- Severe allergic reaction, swelling of face or throat, or trouble swallowing
The manifest sets the skill language to "en" with no indication that users may opt into another language or that the skill is intentionally limited to English for a documented reason. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.
No suspicious patterns detected.