ably

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: 0.90). SKILL.md explicitly instructs the agent to fetch data from Ably (e.g., "Get Message History", "Get Channel Presence" and using "membrane request CONNECTION_ID /path") which returns user-generated/untrusted channel messages and presence info that the agent is expected to read and could materially influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:56 AM