spark

Warn

Audited by Snyk on Mar 24, 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 Step 4 explicitly requires running the bundled Tavily search tool (./spark/tools/tavily-search "<query>") which returns JSON including content scraped from public websites/marketplaces (e.g., Gumroad) and the agent is instructed to parse that untrusted, user-generated third-party content to inform idea selection and market/research decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 24, 2026, 04:31 AM
Issues
1