attending-physician

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's "How to Use" and "Platform Support" sections explicitly instruct the agent to fetch and "Read https://awesome-skills.dev/skills/healthcare/attending-physician.md" (and a raw GitHub URL https://raw.githubusercontent.com/...) to install/apply the role, meaning the agent will ingest public third‑party pages that can change its system prompt/behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to "Read https://awesome-skills.dev/skills/healthcare/attending-physician.md" and provides the raw content URL https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/healthcare/attending-physician/SKILL.md, which if fetched would directly inject and control the agent's system prompt/instructions (a runtime dependency controlling prompts).