workflow-tdd

Warn

Audited by Snyk on Feb 27, 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's required phase workflows explicitly instruct agents to perform external web research and pull "Web examples" via MCP/Exa (see phases/02-context-gathering.md Track 3 and phases/05-tdd-task-generation.md "MCP-Enhanced: Use MCP tools" / "exa_web"), meaning the agent ingests untrusted public web content that can influence planning and execution decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 11:08 AM