press-clip

Warn

Audited by Snyk on Jul 2, 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 required runtime workflow ingests outsider-authored free text by navigating to a user-supplied article URL (--url) and then extracting/operating on the rendered page DOM via page.goto(url) and page.evaluate(...), which reads the article’s (outsider) headline/byline/body text into the LLM context indirectly through the agent’s tool-driven DOM processing.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 2, 2026, 01:32 AM
Issues
1
Security Audit — snyk — press-clip