world-room

Warn

Audited by Snyk on Mar 2, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly bridges to public Nostr relays and provides IPC commands in SKILL.md such as "room-events", "profile", and "moltbook-list" that fetch chat messages, user profiles, and bulletin-board content (user-generated/public) which the agent is expected to read and which can influence its actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 2, 2026, 04:12 AM