skills/mksglu/skills/agents-sdk/Gen Agent Trust Hub

agents-sdk

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to fetch documentation and implementation guides from Cloudflare's official GitHub repository.
  • [COMMAND_EXECUTION]: Provides standard developer instructions for installing the 'agents' SDK and its dependencies via npm.
  • [REMOTE_CODE_EXECUTION]: Describes an experimental 'Code Mode' feature that allows the agent to generate and execute JavaScript code locally to orchestrate complex tool interactions.
  • [PROMPT_INJECTION]: Highlights data ingestion points from emails and MCP servers, which represent an attack surface for indirect prompt injection that requires standard validation practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 04:33 AM