biopython-bio
Warn
Audited by Snyk on Apr 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill explicitly makes remote queries to public NCBI resources (e.g., Bio.Blast.NCBIWWW.qblast and Entrez.esearch/Entrez.read shown in the BLAST and Entrez examples in SKILL.md), ingesting and parsing third-party/public database content that the agent uses to make decisions (e.g., filtering alignments), so untrusted external content could influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata