lev-find

Warn

Audited by Snyk on Mar 1, 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 explicitly mandates using external web research backends (Exa/exa-plus, valyu, deep-research) and references social and scraping tools (grok-research, firecrawl, agent-browser) in SKILL.md, so the agent fetches and ingests public web/GitHub/social/scraped content and synthesizes it into research results and follow-up actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 09:43 AM