ably-realtime

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). This skill's SKILL.md instructs the agent to proxy requests through Membrane to the Ably Realtime API (see "Proxy requests" and the membrane request CONNECTION_ID /path/to/endpoint examples), which will fetch third‑party realtime channel/message data that can be user‑generated and thus could inject instructions that influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:56 AM