research-to-article

Warn

Audited by Snyk on Mar 23, 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.md GATHER phase and references/research-agents.md explicitly require launching parallel research agents and direct WebSearch to collect current news, social media/community reactions, quotes, and public web content, which the pipeline then compiles and uses as context for article generation—i.e., untrusted third‑party content is fetched and directly influences generation.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 23, 2026, 04:38 PM
Issues
1
Security Audit — snyk — research-to-article