The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run local validation scripts, specifically scripts/validate-config.sh and scripts/validate-templates.sh, and executes project-level commands such as npm run generate.- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8). It ingests untrusted user input for template requirements and logic, which is then written into executable .ts and .tsx files via the prompts in 01-add-template.md and 02-modify-template.md.
Ingestion points: User-provided descriptions and code blocks used to define new or modified templates.
Boundary markers: Absent; there are no delimiters or explicit instructions for the agent to ignore potentially malicious instructions embedded in the user's template data.
Capability inventory: The agent possesses Write, Edit, and Bash permissions, allowing a direct path from writing untrusted content to a file and then executing that content through the generator tool.
Sanitization: Absent; the skill does not perform any escaping, validation, or filtering of user-provided content before it is committed to the filesystem.

generator-maintainer