tooluniverse-protein-therapeutic-design

Warn

Audited by Snyk on Mar 29, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches target structures from public third‑party resources (e.g., PDBe_get_uniprot_mappings/RCSBData_get_entry, emdb_search/emdb_get_entry, alphafold_get_prediction) as shown in SKILL.md and DESIGN_PROCEDURES.md and then uses those retrieved structures to drive design decisions (epitope selection, backbone/sequence generation), which exposes the agent to untrusted public web content that can materially influence tool actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 29, 2026, 11:35 PM
Issues
1