meeting-assistant
Warn
Audited by Snyk on Mar 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's advanced "Pre-Meeting Intelligence Chain" (references/advanced-patterns.md, AGENTS.md instruction) explicitly instructs the agent to have a research-assistant "pull public information" (company background, recent news, LinkedIn signals) and feed those findings into meeting briefs, meaning the agent will ingest untrusted third-party web/social content that can influence its briefs and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata