fda-consultant-specialist
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides educational content and local auditing scripts. No malicious behavior, obfuscation, or unauthorized network access was identified.- [INDIRECT_PROMPT_INJECTION]: The auditing scripts (hipaa_risk_assessment.py, qsr_compliance_checker.py, and fda_submission_tracker.py) read untrusted content from the user's project directory to identify compliance gaps. This represents an indirect prompt injection surface where malicious data in audited files could influence agent behavior, though it is limited by the scripts' read-only functionality.
- Ingestion points: Project files scanned by the diagnostic scripts in the scripts/ directory.
- Boundary markers: None identified in the script logic.
- Capability inventory: Local file reading and pattern matching; no network or administrative capabilities.
- Sanitization: None; the scripts perform direct regex matching on file contents.
Audit Metadata