cpt-coding-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and examples. No scripts, executables, or dynamic code execution patterns were found.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted clinical documentation. Ingestion points: Clinical documentation in prompts (SKILL.md). Boundary markers: Absent. Capability inventory: Text-only advice with no dangerous tools (e.g., no file-write or network-send capabilities). Sanitization: Absent.\n- [EXTERNAL_DOWNLOADS]: The documentation references an installation command (npx skills add) targeting the author's own repository (Open-Medica/open-medical-skills), which is a standard vendor resource and consistent with the skill's authorship.
Audit Metadata