Meeting Prep
Warn
Audited by Snyk on Feb 17, 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). Yes — the skill explicitly requires web research ("Use web search for every person and company") and pulls public third‑party content such as LinkedIn profiles/posts and recent news, which are untrusted user‑generated/open web sources the agent will read and interpret.
Audit Metadata