wrangler

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes examples that embed secret values verbatim in CLI commands and connection strings (e.g., echo "secret-value" | wrangler secret put, inline postgres connection string, --origin-password), which would require an LLM to handle or output secrets directly.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs “Wrangler docs” retrieval from a public website (developers.cloudflare.com) and the required runtime workflow would fetch and incorporate that outsider-authored free text into the agent’s LLM context.