The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and improve existing technical documentation, creating a surface for indirect prompt injection where instructions embedded in the input content could influence the agent's behavior during the editing process.\n
Ingestion points: Existing documentation files and metadata located within apps/docs or apps/blog that are provided to the agent for rewriting or improvement.\n
Boundary markers: The skill does not provide instructions for the use of boundary markers or specific 'ignore' directives to isolate the untrusted input content from the system instructions.\n
Capability inventory: The agent is authorized to modify files on the system and execute various development tools and linters, including pnpm, cspell, and bunx.\n
Sanitization: No methods for sanitizing, escaping, or validating the provided input documentation are described in the instructions.

docs-writer