care-coordination-expert
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a specialized persona for healthcare care coordination, focusing on clinical safety and regulatory compliance. It does not contain executable code, scripts, or tool definitions.
- [PROMPT_INJECTION]: The instructions do not attempt to bypass safety filters or override system constraints. On the contrary, the skill explicitly requires the agent to adhere to safety guidelines, clinical governance, and statutory authority.
- [DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive file paths were identified. The document emphasizes privacy principles, data minimization, and secure handling of patient information.
- [EXTERNAL_DOWNLOADS]: There are no commands or instructions that trigger the download of external code or configuration from untrusted sources.
- [COMMAND_EXECUTION]: The skill does not contain any shell commands, subprocess calls, or dynamic execution patterns. It provides instructional logic for decision-making rather than direct system interaction.
- [SAFE]: The skill addresses potential indirect prompt injection surfaces (such as processing healthcare artifacts) by defining clear rejection rules and input validation requirements in Section 12 and Section 28.
Audit Metadata