diabetes-care

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external content (manuscripts and clinical study data), creating a surface for indirect prompt injection.
  • Ingestion points: The skill evaluates manuscripts, trial data, and abstracts provided by the user in SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or instructions to ignore embedded commands within the processed manuscripts.
  • Capability inventory: The skill lacks dangerous capabilities; it does not perform network operations, file writes, or subprocess executions.
  • Sanitization: No explicit sanitization or validation logic is defined for the manuscript content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 11:33 AM
Security Audit — agent-trust-hub — diabetes-care