mat-xrd-digitizer

Warn

Audited by Snyk on Jun 19, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). The runtime LLM ingestion path is the user-provided XRD plot image for VLM peak extraction (outsider-authored free text/image content), which the agent reads to generate peaks.json; the provided script itself only consumes local JSON and does not ingest free text into the LLM.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 19, 2026, 04:48 PM
Issues
1