karpathy-coder

Warn

Audited by Snyk on Aug 21, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text can be ingested when a user runs the linter tools on stdin or a plan file (e.g., assumption_linter.py reads markdown from sys.stdin), which the workflow then analyzes as plain text.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 21, 2026, 05:09 AM
Issues
1
Security Audit — snyk — karpathy-coder