participation-warmup-planner

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow ingests community “public surfaces” via connectors (e.g., scripts/connectors/discourse.py, hn.py, bluesky.py/fediverse.py) and also accepts “User-provided pasted rules/exports,” so outsider-authored free text can be read before any specific item selection by the agent (e.g., the fetched forum/threads/feeds that those connectors return).