The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage the development environment, including installing global packages (npm install -g @angular/cli) and generating project artifacts (npx ng new, npx ng generate).
[INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest external instructions that could be manipulated to alter the agent's behavior.
Ingestion points: The agent is instructed to load data from the ng mcp server, the get_best_practices tool, and AI configuration files (--ai-config) into its memory.
Boundary markers: There are no delimiters or instructions provided to the agent to treat this external data as untrusted or to ignore embedded instructions.
Capability inventory: The agent has the capability to execute shell commands, create files, and modify project structures.
Sanitization: No validation or sanitization steps are defined for the content retrieved from these external sources before it is used to guide code generation.
[EXTERNAL_DOWNLOADS]: Fetches the @angular/cli and tailwindcss packages from the official npm registry, which is a well-known service.
[METADATA_POISONING]: The skill's YAML frontmatter identifies the author as "Angular Team @ Google," which does not match the actual skill author, potentially creating a false sense of officiality.

angular-new-app