agent-prompts
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 prompt templates explicitly instruct agents to ingest and analyze public/untrusted sources such as URLs/RSS feeds, company websites, LinkedIn, news, and user-provided documents (see "Content Summarizer", "Discovery Call Prep", and "Customer Support AI Agent"), meaning the agent would read and interpret third-party web/user-generated content.
Audit Metadata