client-discharge-notes
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a data processor that ingests external clinical notes and medication plans to generate user-facing instructions.
- Ingestion points: Processes untrusted patient data, procedure descriptions, and medication details provided in the user brief (SKILL.md).
- Boundary markers: There are no explicit delimiters or instructions to ignore potential injections within the provided clinical data.
- Capability inventory: The skill is strictly limited to text generation. It does not utilize any tools for network communication, file system modification, or shell command execution.
- Sanitization: No sanitization or input validation logic is present to filter the input data before it is interpolated into the output prompt.
Audit Metadata