oma-design

Warn

Audited by Snyk on May 3, 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 Phase 2 EXTRACT explicitly fetches external vendor templates from the public getdesign catalog (via bunx getdesign@latest per resources/getdesign-fetcher.md) and can also fetch and analyze arbitrary reference URLs (execution-protocol.md Branch C), then loads that external content into the agent's context and uses it to seed proposals and generate the final DESIGN.md, so untrusted third‑party content can materially influence the agent's decisions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 3, 2026, 01:32 AM
Issues
1