alphafold-database

Warn

Audited by Snyk on Apr 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: 0.90). The SKILL.md explicitly instructs the agent to fetch and parse open/public third‑party content (e.g., AlphaFold REST API at https://alphafold.ebi.ac.uk/api/prediction/{uniprot}, UniProt/3D‑Beacons endpoints, and the Google Cloud bucket gs://public-datasets-deepmind-alphafold-v4) and then interpret pLDDT/PAE JSON and other files to drive downstream analysis and selection decisions, so external data could materially influence tool use and actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 29, 2026, 02:23 AM
Issues
1