edge-deployment
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data (e.g.,
package.json) to automate framework detection and build configuration. - Ingestion points: Project configuration files, dependency lists, and directory structure are read into the agent context as described in the framework detection section.
- Boundary markers: The skill does not define explicit delimiters to separate project data from agent instructions when performing framework analysis.
- Capability inventory: The skill utilizes shell execution capabilities via
npx vercel,npx wrangler, andnpmscripts for build and deployment tasks. - Sanitization: Build commands and output paths are derived from project files without additional validation or sanitization.
Audit Metadata