The Agent Skills Directory

[SAFE]: The skill operates as intended for a QA automation tool, following standard practices for bug reporting and issue management.
[COMMAND_EXECUTION]: The skill uses the gh issue create command to file reports on GitHub. This is a legitimate and expected use of development tooling for the skill's stated purpose.
[PROMPT_INJECTION]: The skill processes user-provided bug descriptions and codebase context (e.g., UBIQUITOUS_LANGUAGE.md) to generate issue content. This represents a potential surface for indirect prompt injection, managed through instructional constraints.
Ingestion points: User bug reports and project documentation files like UBIQUITOUS_LANGUAGE.md (SKILL.md).
Boundary markers: No explicit delimiters are used for user input or codebase context.
Capability inventory: The skill uses the gh command-line tool to submit data to GitHub repositories.
Sanitization: The agent is explicitly instructed to avoid internal implementation details like file paths or line numbers, which serves as a basic logic-based filter for the generated output.

qa