messaging-agents

Warn

Audited by Snyk on Feb 17, 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 sends messages to other agents that "can ... make API calls" and "search the web if they have web search tools" (see "The target agent CAN" section), so the agent may receive and must interpret untrusted third-party web/API content in the other agent's responses.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 02:57 PM