amity

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). This skill's SKILL.md explicitly directs the agent to use the Membrane CLI to run actions and proxy requests against Amity (e.g., "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint"), which will fetch user-generated social content (posts, messages, channels) from a third-party platform that the agent may read and act upon.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:58 AM