The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by ingesting data from external sources and using it to guide agent behavior.
Ingestion points: The skill takes input from user arguments ($ARGUMENTS) and scans the local codebase using Glob, Grep, and Read tools to gather context for variations.
Boundary markers: There are no instructions for the agent to use specific delimiters or to disregard instructions that might be embedded within the project files or the user's initial idea.
Capability inventory: The skill can search the filesystem, read files, and write new markdown documents to the docs/ideas/ directory.
Sanitization: The instructions do not include requirements for escaping, filtering, or validating the content retrieved from the codebase before it is interpolated into the reasoning process.

idea-refine