NYC

federation

Warn

Audited by Snyk on Feb 17, 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). This skill explicitly instructs the agent to fetch and dereference actor profiles and collections from arbitrary ActivityPub endpoints (see "Resolve Recipients" / "Discover Inboxes" and the example curl to https://site.com/@username), which ingests public, user-generated content from third-party servers that the agent will read and interpret.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 01:55 PM