brainstorm

Warn

Audited by Snyk on Mar 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: 0.80). The skill's workflow explicitly instructs using a WebSearch to find external references (see "Tools" table and Phase 4 — Reference in SKILL.md and references/QUESTIONING-GUIDE.md), meaning the agent may fetch and incorporate untrusted public web content into prompts or decisions, creating a route for indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 14, 2026, 09:35 AM
Issues
1