score-optimizer

Warn

Audited by Snyk on Jun 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: 0.85). Outsider free text is the user-provided sample article bodies in assets/articles/samples/*.md; scripts/run_scoring.py reads each .md and injects its full contents into the LLM prompt ({article_content} in full_prompt).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 13, 2026, 09:35 AM
Issues
1
Security Audit — snyk — score-optimizer