what-would-lenny-do

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to query and read external archive content via lennysdata tools (e.g., lennysdata:search_content, lennysdata:read_content, lennysdata:list_content), which fetches public third‑party newsletter/podcast material that the agent must interpret and use to drive recommendations — exposing it to untrusted third‑party text that could contain instructive payloads.