workers-best-practices

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches best practices and documentation from Cloudflare's official developer portal (developers.cloudflare.com) and type definitions from the official NPM registry (@cloudflare/workers-types). These resources originate from established technology companies and well-known services.
  • [COMMAND_EXECUTION]: Utilizes standard development CLI tools including npm, tar, and npx tsc to manage type definitions and perform code validation. These operations are part of a routine development workflow and are executed with static arguments.
  • [PROMPT_INJECTION]: Evaluated for indirect prompt injection risk as the skill ingests user-provided code and configuration files. Ingestion points: Processes Cloudflare Workers source files and wrangler.jsonc during the review workflow. Boundary markers: Absent in instructions. Capability inventory: Hardcoded shell commands (npm, tar, npx) and network fetches to well-known domains. Sanitization: None mentioned. The risk is minimized because the skill's operations are fixed and do not execute code or logic derived from the content being analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 11:56 PM
Security Audit — agent-trust-hub — workers-best-practices