The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources including GitHub issues, Linear tasks, and Jira tickets. While these are trusted platforms, the content within them (issue descriptions/comments) is user-generated and could theoretically contain instructions designed to influence the agent's behavior.
Ingestion points: GitHub issue body (via gh issue view), Linear issue body (via mcp__plugin_linear_linear__get_issue), and Jira page content (via WebFetch).
Boundary markers: The skill defines a strict Markdown template for the output spec, which helps constrain the agent's output, though it does not explicitly instruct the agent to ignore commands within the fetched text.
Capability inventory: The skill is limited to reading data and generating text; it explicitly mandates a 'pause' for user approval before moving to any implementation steps.
Sanitization: No explicit sanitization of fetched text is performed before processing.
[COMMAND_EXECUTION]: The skill uses the gh (GitHub CLI) to retrieve issue details. This is a standard developer workflow and the execution is restricted to viewing issue data in JSON format.

spec