bindingdb-database
Warn
Audited by Snyk on Jun 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow ingests outsider-authored free text only if it downloads/loads BindingDB content (e.g.,
load_bindingdb("BindingDB_All.tsv")from the public BindingDB download URL or REST API JSON), which is public web content authored/curated by third parties and then converted into LLM-readable strings/fields like SMILES/target names.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata