ez-lobsters

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

• Third-party content exposure detected (high risk: 0.80). The CLI fetches and displays user-generated content from the public Lobste.rs API (see LOBSTERS_API "https://lobste.rs" and functions fetch_stories/fetch_story in scripts/lobsters.py and the SKILL.md commands), so the agent ingests and interprets untrusted third-party posts/comments as part of its workflow which could influence subsequent decisions.