security-skill-scanner

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

• Third-party content exposure detected (high risk: 0.80). The skill's moltbook-monitor.sh explicitly fetches and parses public, user-generated posts from https://www.moltbook.com/api/v1/posts (see moltbook-monitor.sh and data/moltbook-security-posts.json), meaning the agent ingests and displays untrusted third-party content that could carry indirect prompt-injection.