The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/validate_vue.py executes vue-tsc and stylelint via the run_command helper in scripts/_skill_cli.py. This implementation is secure as it uses shutil.which to resolve absolute paths for executables and explicitly disables shell execution (shell=False), preventing common command injection and path manipulation vulnerabilities.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project files (.vue, .css, .scss) through the validate_vue tool. While this represents an attack surface for indirect prompt injection via compiler/linter output, the risk is inherent to development tools and is mitigated by the tool's limited scope and secure execution environment.

primevue-openprops-architect