website-repo

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses variables from $ARGUMENTS and site-config.json to construct shell commands like 'cd ' and 'gh repo create '. Without sanitization, malicious inputs could lead to command injection.
  • [COMMAND_EXECUTION]: Indirect Prompt Injection Surface: 1. Ingestion points: $ARGUMENTS and site-config.json. 2. Boundary markers: Absent. 3. Capability inventory: Bash, git, gh CLI, Read, Write, Edit. 4. Sanitization: Absent.
  • [SAFE]: The skill includes explicit validation steps to prevent sensitive files like .env and node_modules from being staged or committed to Git.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:27 PM
Security Audit — agent-trust-hub — website-repo