project-scaffolding

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill possesses a significant attack surface for indirect prompt injection and potential command injection by ingesting untrusted user input to drive CLI operations.
  • Ingestion points: User-provided inputs for 'Project name', 'Location/directory', 'Description', and 'Author name' in Step 2.
  • Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within user-provided metadata.
  • Capability inventory: Extensive use of shell commands including mkdir, cd, touch, and various framework CLIs (npx, npm, cargo, go, flutter, spring).
  • Sanitization: No explicit sanitization or validation logic is mentioned for user-supplied strings before they are interpolated into commands or file content.
  • Command Execution (SAFE): The skill executes various CLI commands to scaffold projects. While command execution is inherently risky, these actions are essential to the primary purpose of the skill and utilize standard, well-known ecosystem tools (e.g., npx create-next-app, cargo new).
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 08:29 PM