The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several standard command-line tools for its workflow. It uses git add, git commit, and git worktree to manage specification documents in the repository as shown in SKILL.md. It fetches data using the gh (GitHub CLI) tool to view issue details. Additionally, it performs local codebase exploration using grep, ls, and xargs in workflows/brainstorm.md to identify relevant models and patterns.
[PROMPT_INJECTION]: The skill presents an attack surface for Indirect Prompt Injection (Category 8) because it processes external data.
Ingestion points: Untrusted content is ingested from GitHub issue titles and bodies via the gh issue view command in SKILL.md.
Boundary markers: The skill does not implement explicit boundary markers or delimiters to isolate the issue content from the agent's instructions.
Capability inventory: The skill has access to local file discovery and version control modification capabilities through git, grep, and ls.
Sanitization: External content from GitHub is processed without evidence of sanitization or validation before being used to generate the specification document.

spec