microsite

Warn

Audited by Snyk on Feb 27, 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 workflow (Step 3: "Tier 1: browser-use" and "Tier 2: WebFetch") and the Octave context gathering (tools like list_resources / search_resources which include URLs and Google Drive files) explicitly fetch and parse target company websites and arbitrary uploaded/public URLs, meaning the agent will ingest open third-party web content and use it to shape messaging and actions for the generated microsite.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 03:09 AM