minimax-search
Warn
Audited by Snyk on Apr 3, 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 explicitly calls the MiniMax web search API (POST https://api.minimaxi.com/v1/coding_plan/search) as documented in SKILL.md and implemented in scripts/search.ts, ingesting and iterating over organic search results (title/snippet/link) from public websites which the agent reads/prints and can use to drive further actions, so it consumes untrusted third‑party content that could inject instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata