cloudbase-agent

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: 0.80). The skill includes server-side HTTP tools and explicit "search_web"/HttpTool examples (py/references/tools.md, py/adapter-langgraph.md, and recipes) and describes tool-calling patterns where tool results from arbitrary URLs or third-party APIs are fed back into agent flows (Tool Calling Pattern), meaning the agent will ingest untrusted public web/API content that can influence subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 3, 2026, 03:47 PM
Issues
1