enrichment-design

Warn

Audited by Snyk on Mar 3, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md and references/data-point-library.md explicitly instruct a "research_pro" agent to fetch and interpret public web content (e.g., company careers pages, news sites, LinkedIn posts, job boards, G2 reviews) to produce evidence-backed column outputs that drive hypothesis scoring and downstream actions, exposing the agent to untrusted third-party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 02:47 PM