experiment-pipeline

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

• Third-party content exposure detected (high risk: 0.90). Flagged because the Stage 1 workflow explicitly instructs the agent to find and run baseline code from public repositories and re‑implementations (e.g., "Find the original baseline code (official repo, re-implementations...)" in SKILL.md and references to GitHub / Papers With Code in references/stage-protocols.md), which requires fetching and interpreting untrusted, user‑generated third‑party content that can materially influence execution and tool use.