kimi-search

Warn

Audited by Snyk on Mar 22, 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 uses the Kimi $web_search builtin (documented in SKILL.md and implemented in scripts/kimi-search.py) so the agent ingests real-time open-web search results from public sites via Moonshot, which are untrusted/third-party content that can influence model behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 22, 2026, 01:08 PM
Issues
1