protein-sequence-similarity-search
Warn
Audited by Snyk on May 19, 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). The skill automatically submits queries to and ingests results from public third‑party APIs (ColabFold MMseqs2 at https://api.colabfold.com and EBI BLAST at https://www.ebi.ac.uk/Tools/services/rest/ncbiblast), parses A3M/JSON and hit description fields, and explicitly reads the generated .md/.json outputs as part of its required workflow, so untrusted external content can influence interpretation and downstream actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata