debrief

Warn

Audited by Snyk on Mar 1, 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 required workflow explicitly runs Phase 2 "Market Research" using WebSearch (Tools Used) and the research query templates in references/research-queries.md to gather and incorporate public web links and documentation into references.md, so the agent will fetch and interpret open/public third-party content that can influence decisions and outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 08:41 PM