presentation-generation
Warn
Audited by Snyk on Feb 20, 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 SSE event docs (references/SSE-EVENTS.md) explicitly include web_search_query and web_search_citations events showing the agent performs web searches and ingests/publicly cites arbitrary URLs from the open web, which the agent then uses to produce responses and thus could enable indirect prompt injection.
Audit Metadata