The Agent Skills Directory

[SAFE]: No malicious code, obfuscation, or unauthorized data access patterns were found in the skill's instructions or reference files.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests user input and writes it to a design document. * Ingestion points: User responses to the Startup and Builder mode questions defined in SKILL.md. * Boundary markers: The skill does not use specific delimiters to wrap user input or include instructions for the agent to ignore instructions embedded within those answers. * Capability inventory: The agent is instructed in SKILL.md to write documentation files to the ./docs/design/ directory. * Sanitization: There are no explicit instructions for sanitizing or escaping user-provided content before it is interpolated into the document template. This is considered a low-risk surface given the primary purpose of generating local documentation.

office-hours