create-rfd

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

• Third-party content exposure detected (high risk: 0.80). This skill's required workflow instructs the agent to "Research each option" and to reference external/public resources (see "Step 4. Research Options" and the examples/references in SKILL.md and references/process.md, which cite external sites like redis.io/AWS and suggest creating GitHub discussions), meaning the agent will ingest open/public third‑party web content and use it to make recommendations and drive state transitions.