content-scout

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 3 explicitly requires searching and ingesting open/public sources (e.g., "Dev blogs, Hacker News, personal engineering blogs, ... Practitioner X/Twitter threads"), and those untrusted third‑party articles are read and interpreted to score, rank, and draft social posts (Steps 4–5), so external content can materially influence agent decisions and outputs.