youmind-deep-research
Warn
Audited by Snyk on Mar 17, 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 skill's workflow (SKILL.md Steps 3–5 and the polling progress messages) explicitly runs YouMind's "research" tool that "gathers sources from across the web" and returns a researchResult which the agent must read/summarize, meaning it ingests untrusted public web content (youmind.com-sourced pages) that could carry indirect prompt-injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata