The Agent Skills Directory

[COMMAND_EXECUTION]: The skill incorporates the use of the Salesforce CLI (sf) and Node.js (npm) within its documented workflow to deploy components and execute Jest tests.
[INDIRECT_PROMPT_INJECTION]: The skill generates code based on user specifications, which constitutes a vulnerability surface for processing untrusted data.
Ingestion points: User requirements for LWC scaffolding as defined in SKILL.md.
Boundary markers: Absent; the instructions do not provide delimiters or safety warnings for user-provided data.
Capability inventory: File system modification (Write) and shell command execution (Bash(sf *), Bash(npm *)) as defined in the skill workflow.
Sanitization: Absent; user input is directly used to influence the generated component code.
[DYNAMIC_EXECUTION]: The skill references patterns for runtime code loading, such as dynamic component imports and loading external libraries from static resources.
Evidence: references/lwc-patterns.md details the usage of import() for dynamic components and loadScript() for third-party libraries.

sf-lwc