tooluniverse-antibody-engineering

Warn

Audited by Snyk on Mar 13, 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.md explicitly requires calling public third‑party resources (Phase 0 and numerous code examples: IMGT_search_genes/IMGT_get_sequence, iedb_search_epitopes, SAbDab/TheraSAbDab searches, UniProt, AlphaFold_get_prediction, PubMed_search) and uses those untrusted web-sourced results to drive humanization, epitope prediction, design decisions and tool use, so external content can materially influence the agent's actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 03:47 AM
Issues
1