workers-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code and configuration files during the review process.
- Ingestion points: Analyzes Cloudflare Workers source code and wrangler.jsonc files provided in the project context.
- Boundary markers: The instructions do not define specific delimiters to isolate user-provided code, though the review is guided by a structured rule-based framework.
- Capability inventory: The skill utilizes terminal commands such as npm, npx, and tar to fetch types and perform validation.
- Sanitization: No explicit sanitization of the reviewed content is described, relying instead on the agent's instruction to follow best practice rules.
- [EXTERNAL_DOWNLOADS]: The skill retrieves documentation and type definitions from trusted domains to ensure up-to-date analysis.
- Downloads: Fetches the @cloudflare/workers-types package from the official npm registry and references documentation at developers.cloudflare.com.
- [COMMAND_EXECUTION]: The skill suggests using standard development tools to assist in the code review and environment setup.
- Subprocess calls: Employs npm pack and tar to retrieve and extract type definitions, and uses cat to read local configuration files.
- Validation tools: Recommends running npx tsc, npx eslint, and npx oxlint for static analysis and adherence to standards.
Audit Metadata