skills/involvex/skills/sandbox-sdk/Gen Agent Trust Hub

sandbox-sdk

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @cloudflare/sandbox NPM package and utilize the official cloudflare/sandbox Docker image, which are components provided by a well-known service provider.
  • [COMMAND_EXECUTION]: Implements code and shell command execution capabilities via sandbox.runCode() and sandbox.exec() within isolated containers, which is the stated purpose of the SDK.
  • [DATA_EXFILTRATION]: Documents APIs for reading files from the sandbox and exposing ports for network service previews. These are documented neutrally as standard features of the environment.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection due to its core function of executing external code. 1. Ingestion points: sandbox.runCode and sandbox.writeFile (SKILL.md). 2. Boundary markers: Not present in the generic API examples. 3. Capability inventory: Shell execution, code interpreter, file system access, and port exposure (SKILL.md). 4. Sanitization: Not provided in basic usage snippets. This represents a known attack surface for any code-execution tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 09:58 PM