project-development

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: 1.00). The skill's "Acquire" stage and Example 1 (Karpathy's HN Time Capsule) explicitly describe fetching and analyzing public Hacker News discussions and other external web sources—user-generated, untrusted content that the agent would ingest and interpret—exposing it to potential indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 10:38 AM