adaptyv

Warn

Audited by Snyk on Apr 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: 0.70). The skill's required workflows (notably reference/protein_optimization.md and the examples) explicitly call and ingest data from public third-party services (e.g., NetSolP at services.healthtech.dtu.dk, SoluProt/SolubleMPNN/ESM/AlphaFold calls and the unspecified download_urls returned by the Adaptyv API) and then use those responses to rank/select sequences and drive subsequent actions, so external untrusted content can materially influence agent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 2, 2026, 01:57 AM
Issues
1