The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files which could be manipulated to influence agent behavior.
Ingestion points: The implementation, progress, phase, and status subcommands in references/detailed-guide.md read from docs/{name}/RESEARCH.md, docs/{name}/IMPLEMENTATION.md, and docs/{name}/PROGRESS.md to determine next steps and implementation details.
Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions that might be embedded within the content of these external files.
Capability inventory: The skill utilizes file system write access (to create the docs/ folder and its contents), web search tools for research phases, and general code implementation and testing capabilities (which typically involve terminal command execution).
Sanitization: No sanitization or validation of the content within the read files is performed before the agent processes the content to guide its implementation tasks.

build