json-toolkit

Warn

Audited by Snyk on Mar 7, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill explicitly accepts JSON from stdin (main.py: "use
  • for stdin") and the SKILL.md includes a "Pipe from curl" example (curl -s https://api.example.com/data | python main.py
  • ...), which demonstrates ingesting arbitrary public web API content that is untrusted and can be parsed and acted on by the tool.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 12:33 PM