Integrates with E2B's cloud sandbox infrastructure to provide secure, isolated code execution environments. Offers tools for creating and managing sandboxes with customizable timeouts and templates, executing Python code using Jupyter Notebook syntax, and running shell commands. Useful for AI applications that need to safely execute user-generated code, perform data analysis, or run system commands without compromising the host environment.
Cognium trust score
94%
Tier
Verified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-28.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.