alterlab-biopython

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

• Third-party content exposure detected (high risk: 0.90). The skill's documentation and required workflows explicitly instruct using Bio.Entrez (e.g., references/databases.md) and Bio.Blast.NCBIWWW.qblast (references/blast.md) to fetch and parse public NCBI resources (GenBank, PubMed, BLAST results), which the agent is expected to read/interpret and use to drive follow-up actions (e.g., selecting top hits and fetching sequences), exposing it to untrusted third‑party content that could carry indirect prompt injection.