deploy-cloudflare
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [External Downloads] (LOW): The skill recommends installing the 'wrangler' package via npm. This is a standard tool for the service but unversioned external downloads are a minor risk.
- [Command Execution] (LOW): The skill uses the 'Bash' tool for deployment and management, providing the agent with significant system access.
- [Prompt Injection] (LOW): The skill contains a surface for indirect prompt injection. 1. Ingestion points: The agent is instructed in SKILL.md to read local project files and directory contents (e.g., wrangler.toml, ./dist) via Read, Glob, and Grep tools. 2. Boundary markers: Delimiters or 'ignore instructions' warnings are absent in the skill instructions. 3. Capability inventory: The skill utilizes high-privilege tools including Bash, Write, and Edit, which can be misused if file contents are malicious. 4. Sanitization: No validation or escaping of external file contents is specified before the data is processed or used in shell commands.
Audit Metadata