federation

Warn

Audited by Snyk on Apr 28, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs fetching and dereferencing arbitrary ActivityPub actor profiles and collections (see "Server-to-Server Federation" — "Resolve Recipients" and "Discover Inboxes") so the agent will ingest untrusted, user-generated third‑party content (actor pages) and use it to decide delivery and processing actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 28, 2026, 03:12 PM
Issues
1