data-engineering-streaming

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md includes an MQTT subscriber/publisher example that connects to the public broker "broker.emqx.io" and decodes/acts on incoming JSON messages (untrusted, user-generated content), meaning the agent would ingest and process third-party data that could influence its actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 03:18 PM