raf-score-calculator
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions do not contain any attempt to override agent behavior, bypass safety filters, or extract system prompts. The language is purely clinical and instructional.
- [DATA_EXFILTRATION]: No network tools (curl, wget, etc.) or sensitive file paths are referenced. The skill operates within the agent's context to calculate scores based on provided clinical data.
- [EXTERNAL_DOWNLOADS]: The skill references the official GitHub repository for 'Open-Medica', which is consistent with the author and vendor context provided. No untrusted third-party code is downloaded.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external 'clinical notes' and 'encounter documentation'. While this represents an ingestion surface for potentially untrusted data, the skill has no exploitable capabilities such as file system writes, network access, or command execution. The risk is limited to potential output manipulation within the chat context.
Audit Metadata