The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill establishes project context by reading local files which could contain untrusted data.
Ingestion points: The skill reads README, package.json, and pyproject.toml from the project directory during the 'Step 1: Initial Understanding & Context Gathering' phase.
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content within these files.
Capability inventory: The skill has the ability to read local files, interact with the user via AskUserQuestion, and write new markdown files to the docs/ directory.
Sanitization: There are no explicit instructions for sanitizing or validating the content retrieved from project files before it is used to influence the quality scoring or PRD generation.

product-requirements