boltz
Warn
Audited by Snyk on Jul 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required runtime workflow can call
--use_msa_server, which fetches MSAs from the public ColabFold API (api.colabfold.com) and injects that fetched text (MSA content) into the model pipeline/LLM context, making it outsider-authored free text from a public web service.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata