development-workflow
Warn
Audited by Snyk on Feb 16, 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 workflow's Step 1 (skill-researcher) explicitly instructs performing web searches and GitHub/MCP server research—ingesting public web pages and repositories that the agent will read and synthesize—so it clearly consumes untrusted third‑party content.
Audit Metadata