wrangler
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides informational documentation and command-line examples for the Cloudflare Wrangler CLI. All scripts and commands are legitimate tools for managing the Cloudflare platform.
- [SAFE]: The skill explicitly recommends security best practices, such as using
.dev.varsfor local secrets and thewrangler secretcommand for production credentials, which helps prevent accidental credential exposure. - [PROMPT_INJECTION]: The skill enables an agent to interact with external data sources, such as live logs (via
wrangler tail) or database query results (viawrangler d1 execute). This identifies a surface for indirect prompt injection from untrusted external content, which is a common risk for agents performing observability or data retrieval tasks, but it is not a direct flaw in the skill itself.
Audit Metadata