The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) and jq to list, filter, and modify repository issues. This behavior is consistent with the skill's stated purpose of backlog hygiene.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting and acting upon untrusted data from GitHub issues. 1. Ingestion points: Issue titles and bodies are retrieved via gh issue list (SKILL.md, Process steps 3, 4, 5). 2. Boundary markers: No delimiters or instructions to ignore embedded commands are present in the provided process. 3. Capability inventory: The skill can execute gh issue close and gh issue edit based on its logic. 4. Sanitization: No explicit content sanitization or validation is identified before the agent processes the retrieved issue data.

tidy