amara

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: 1.00). The SKILL.md explicitly instructs using Membrane actions and proxy requests (e.g., "Get Subtitles", "List Video URLs", and membrane request CONNECTION_ID /path/to/endpoint) to fetch content from Amara (a public platform with user-generated subtitles/videos), meaning the agent will ingest untrusted third-party content that could influence its actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:55 AM