NYC

sparc-methodology

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: 0.90). The skill's "researcher" mode explicitly performs parallel WebSearch/WebFetch and stores research findings (e.g., news/industry/academic sources and links to GitHub/NPM/Discord), so the agent fetches and ingests open public third‑party content that could include untrusted, user-generated material and enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:24 AM