stepback

Warn

Audited by Snyk on May 14, 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 Step 3 explicitly mandates spawning a research agent (Perplexity) to run web queries and ingest public web results, so the agent will fetch and interpret untrusted third‑party web content that can influence decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 14, 2026, 07:41 AM
Issues
1