rowan

Warn

Audited by Snyk on Apr 3, 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 public protein structures from the RCSB PDB (see references/proteins_and_organization.md and SKILL.md’s create_protein_from_pdb_id / protein.refresh flows), which are third‑party, user‑submitted content that the agent ingests and uses to drive docking/cofolding workflows and thus can materially affect subsequent tool actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 3, 2026, 02:56 AM
Issues
1