robius-matrix-integration

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to handle external data from Matrix homeservers, which constitutes an untrusted data ingestion surface.
  • Ingestion points: Incoming message events and room metadata processed in spawn_timeline_subscriber and enqueue_rooms_list_update within SKILL.md.
  • Boundary markers: The provided snippets do not define explicit boundary markers or instructions to ignore embedded commands within incoming Matrix messages.
  • Capability inventory: The skill utilizes network communication (Matrix SDK), file system writes (SQLite storage in build_client), and asynchronous process management (Tokio tasks).
  • Sanitization: No explicit sanitization or filtering logic for incoming timeline content is presented in the integration examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 05:59 AM
Security Audit — agent-trust-hub — robius-matrix-integration