defi-risk-assessment

Warn

Audited by Snyk on Mar 5, 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). SKILL.md explicitly instructs the agent to consult external public sites (e.g., "Agent Tips" — "Check DeFi Llama for TVL trends") and provides links to defillama.com, rekt.news, app.sperax.io, indicating the agent is expected to fetch and interpret untrusted third‑party web content that can materially influence risk assessments.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 07:55 AM