project-development

Warn

Audited by Snyk on Mar 9, 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 canonical pipeline ("Acquire" stage) and Example 1 explicitly describe fetching and analyzing public/user-generated sources (e.g., Hacker News discussions, external GitHub/Vercel links), so the agent would ingest untrusted third‑party content that it must read/interpret and that can materially influence downstream LLM processing and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 07:20 AM