ai-dev-tools-sync
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: 0.80). The skill's Step 2 explicitly instructs the agent to "Search web for" Copilot feature queries (e.g., "GitHub Copilot features setup 2026"), requiring fetching and reading open web content (public pages/forums) as part of its workflow and thus exposing the agent to untrusted third-party input.
Audit Metadata