The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes dynamic context injection to execute shell commands at load time for repository state discovery.
Evidence: Found !git status --short --untracked-files=all in Phase 1 and `!`find .ai/docs -type f -name 'design-*.md' 2>/dev/null | sort | tail -80 in Phase 1.
Context: These commands are benign and are used to provide the agent with relevant architectural context from the current working directory.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to read and synthesize information from existing codebase files and documentation which could contain malicious instructions.
Ingestion points: The skill reads project-local instructions (AGENTS.md), style guides, and existing design documents located via the find command.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content within the files it researches.
Capability inventory: The skill has the ability to execute shell commands (git, find, test, rg) and create/edit files (design documents).
Sanitization: No sanitization or validation of the content read from the repository is performed before processing.

code-design