nostr-social-graph

Warn

Audited by Snyk on Mar 7, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and processes public, user-generated Nostr events and relay metadata from open indexer/relay URLs (see SKILL.md "Implement the Outbox Model" / "Workflow" steps and references/outbox-model.md resolveRelayList/buildFeedSubscriptions which query well-known public relays like wss://purplepag.es and pool.querySync(INDEXER_RELAYS)), and that third-party content is parsed and used to decide subscriptions, relay routing, and publishing behavior—allowing indirect instructions in incoming events to influence agent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 11:09 PM