NYC

swarm-planner

Warn

Audited by Snyk on Feb 19, 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). The skill's required "Documentation retrieval (REQUIRED for external dependencies)" step instructs the agent to use the Context7 skill or MCP to fetch current external library/framework/API documentation from public websites, which the agent must read and which could contain untrusted third-party instructions that materially influence planning and tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 04:09 AM