bioinformatics-fundamentals

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses data from public third‑party sources (e.g., GenomeArk public S3 via aws s3 cp in SKILL.md's fetch_* functions and example commands) and instructs manual literature searches (PubMed/ResearchGate) — those untrusted external files and pages are read and validated by the agent and their parsed QC values (GenomeScope/BUSCO/Merqury) are used to drive decisions, so it exposes the agent to untrusted third‑party content that could carry indirect prompt‑injection.