browser-search-and-handoff
Warn
Audited by Snyk on May 28, 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). The skill’s runtime browser workflow (
agent-browserin step 3) will fetch and read third-party listing/action pages (public web content authored by outsiders), and then store/return their text/attributes in the LLM context for scoring and handoff.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata