The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via $ARGUMENTS to define the structure and content of generated Angular components.\n
Ingestion points: User-provided strings in $ARGUMENTS used to determine table names and data models in SKILL.md.\n
Boundary markers: The skill uses markdown code blocks for component templates but lacks explicit instructions to the agent to disregard instructions potentially embedded within the user data.\n
Capability inventory: The skill has permission to use the Write tool to create filesystem artifacts and Bash to execute nx or ng build commands.\n
Sanitization: There is no evidence of input validation or sanitization for user-provided identifiers before they are interpolated into the generated TypeScript, HTML, and build scripts.

build-table