fda-consultant-specialist
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and provided scripts do not contain any malicious code, command execution, or data exfiltration patterns. All files are either informational or placeholders.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external medical device documentation and HIPAA-related data.
- Ingestion points: FDA submission documents, Quality System Regulation (QSR) records, and Protected Health Information (PHI) data flow analysis maps (SKILL.md).
- Boundary markers: None identified in the prompt instructions to isolate untrusted external data.
- Capability inventory: Local Python script execution for submission tracking, compliance checking, and risk assessment (SKILL.md).
- Sanitization: No explicit sanitization or validation logic is defined for the external inputs.
Audit Metadata