skills/different-ai/openwork/agent-first-screenshots/Snyk

agent-first-screenshots

Warn

Audited by Snyk on Aug 15, 2026

Risk Level: MEDIUM

Full Analysis

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

Third-party content exposure detected (medium risk: 0.30). In scripts/capture-verify.mjs, runtime reads untrusted text from the outsider-provided specJson CLI argument (parsed via JSON.parse into spec.preCapture), then directly executes it in the page via Runtime.evaluate before capturing the screenshot.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Aug 15, 2026, 02:19 AM

Issues

1

Security Audit — snyk — agent-first-screenshots