browser
Warn
Audited by Snyk on Jul 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md describes a runtime workflow where the agent starts a Chromium session, navigates to (runtime-chosen) web pages, snapshots the page accessibility tree, and reads captured console/network text—i.e., outsider-authored web page content is ingested into the agent’s LLM context via
browser::snapshot/browser::console::read/browser::network::readoutputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata