ultra-research

Warn

Audited by Snyk on Mar 1, 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 explicitly automates Playwright to navigate and extract content from public third‑party sites and searches (e.g., chatgpt.com, gemini.google.com, grok.com including X/Twitter DeepSearch, and WebSearch/WebFetch) as described in Part 2 and the reference files (references/grok.md, references/extraction.md), and it ingests those user-generated/public webpage results and links to drive follow-up queries and reporting—meeting all conditions for exposure to untrusted third‑party content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 06:33 PM