The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill features a documentation generation surface that relies on user-provided descriptions and context. \n- Ingestion points: Untrusted data enters the agent context through user responses during interviews and by reading existing files in the .project/ directory as specified in SKILL.md. \n- Boundary markers: The workflow does not specify the use of delimiters or 'ignore' instructions for the data being ingested. \n- Capability inventory: The agent utilizes file-system write operations across all scripts to generate the .project/ documentation structure. \n- Sanitization: The instructions do not define any filtering, validation, or escaping of the user-provided content before writing it to files.

project-creator