extract

Warn

Audited by Snyk on Mar 9, 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's required workflow (SKILL.md and references/extraction-steps.md, Step 1 and Step 2) explicitly opens arbitrary target URLs with agent-browser and reads the page DOM/stylesheets (getComputedStyle(), CSS @keyframes, screenshots) from public websites and then uses that extracted content to drive analysis and generate outputs, which means untrusted third‑party page content can materially influence the agent's decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 04:58 AM