autonomous-review

Warn

Audited by Snyk on Mar 15, 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 mandatory E2E verification flow (SKILL.md and references/e2e-verification.md) directs the agent to extract a "preview URL" from PR comments and navigate that arbitrary URL via Chrome DevTools MCP, inspect and interpret page content (take screenshots, verify visible outcomes) and use those results to mark acceptance criteria and decide PASS/FAIL, which clearly consumes untrusted third‑party web content that can influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 15, 2026, 11:48 AM
Issues
1