The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes local shell utilities and version control tools to perform its intended functions.
Evidence: Employs git and the GitHub CLI (gh) for managing labels, creating issues, and listing repository state.
Evidence: Uses find, grep, and read to explore and understand the project structure and conventions.
[SAFE]: No malicious behaviors such as credential exfiltration, obfuscation, or persistence mechanisms were detected. The use of external tools is restricted to well-known developer utilities.
[PROMPT_INJECTION]: The skill processes data from the local codebase, which presents a surface for indirect prompt injection.
Ingestion points: The agent reads source code, README.md, and AGENTS.md files in the Workflow section.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the files it reads.
Capability inventory: The skill has the ability to write to the repository's GitHub issue tracker using gh issue create.
Sanitization: The instructions do not specify a sanitization process for data read from the codebase before it is used in issue descriptions.

issue-plan