medical-entity-extractor
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs its stated purpose of medical entity extraction without any suspicious behaviors. No obfuscation, unauthorized network calls, or persistence mechanisms were found.
- [PROMPT_INJECTION]: The skill ingests untrusted data via the 'body' field of patient messages (SKILL.md). This constitutes an indirect prompt injection surface. However, the risk is negligible because the skill is restricted to producing structured JSON output and does not possess capabilities such as shell execution, file system modification, or non-whitelisted network access.
- [DATA_EXFILTRATION]: The skill processes sensitive medical information (PHI). It transparently notes that data is sent to the Claude API for LLM inference, which is a well-known service and the expected behavior for this type of AI agent skill.
Audit Metadata