consultant

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill's Execution Algorithm (SKILL.md §4 ANALYZE: "Use web search for external data when relevant") and CLAUDE.md ("directs Claude to web search at runtime" for current-year benchmarks) explicitly require fetching and ingesting public web sources as part of the analysis workflow, which can include untrusted third-party content that will be read and used to drive decisions and next actions.