prior-auth-readiness-checker

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is comprised entirely of markdown-based instructions. No scripts, binaries, or automated configuration files were found across the analyzed files.
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze potentially untrusted clinical documentation, which represents a surface for indirect prompt injection.
  • Ingestion points: Clinical documentation notes, patient information, and provider information defined in the 'Required Inputs' section of SKILL.md.
  • Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore instructions within the clinical data.
  • Capability inventory: None; the skill does not include any tools, shell commands, network operations, or file system access.
  • Sanitization: Absent; there are no instructions for validating or cleaning the provided clinical inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 04:57 AM
Security Audit — agent-trust-hub — prior-auth-readiness-checker