contributing-to-pi

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly tells the agent to read public GitHub issues/comments using the "gh issue view" command (and even references a public X/Twitter post URL), so the agent is required to ingest and act on user-generated, untrusted third‑party content from GitHub/X as part of its workflow.