lead-scoring

Warn

Audited by Snyk on Mar 18, 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.md explicitly requires web research for Dimension 2 ("This dimension requires web research via search MCP" and "NEVER score leads without checking Dimension 2 via web search") and the evaluation examples reference public sources (LinkedIn posts, TechCrunch, job listings, funding announcements, pricing pages), so the agent will fetch and interpret untrusted, user-generated/public web content that can change scoring and routing decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 10:21 PM
Issues
1