workers-best-practices

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to manage temporary files and extract type definitions from downloaded packages using npm pack and tar. It also utilizes developer utilities such as npx wrangler, npx tsc, and npx eslint for code and configuration validation.- [EXTERNAL_DOWNLOADS]: Documentation is fetched from Cloudflare's official documentation site and the @cloudflare/workers-types package is retrieved from the public npm registry.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external documentation and user-supplied Workers code.
  • Ingestion points: Content from https://developers.cloudflare.com/workers/ and user project files like wrangler.jsonc and source code.
  • Boundary markers: None explicitly defined in the instructions for the agent to separate instructions from processed data.
  • Capability inventory: The skill can execute shell commands (npm, npx, tar, cat) and perform file system operations in /tmp.
  • Sanitization: No specific sanitization or escaping mechanisms are mentioned for the processed documentation or user code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 06:07 AM