code-style
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). The skill explicitly describes processing incoming ActivityPub activities via inbox handlers and REST endpoints and fetching remote actor data (e.g., get_remote_metadata_by_actor(), Webfinger::resolve()), which means it ingests public, user-generated content from arbitrary remote servers and therefore could expose the agent to indirect prompt injection.
Audit Metadata