The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh api) to perform write operations, including creating and updating issues and project items. These commands are necessary for the skill's primary function and use the user's local authenticated session.
[PROMPT_INJECTION]: The skill ingests untrusted data from external sources when reading GitHub issues and comments, creating a potential surface for indirect prompt injection.
Ingestion points: GitHub issue details and comments are retrieved using the mcp__github__issue_read tool (specified in SKILL.md).
Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within ingested issue content.
Capability inventory: The agent has the capability to execute administrative actions via gh api and mcp__github__projects_write tools.
Sanitization: No explicit sanitization or validation of ingested Markdown or text content is performed before processing.
[EXTERNAL_DOWNLOADS]: The documentation in references/images.md suggests using puppeteer-core, a standard Node.js library, for programmatic screenshot generation. This is presented as a developer reference rather than an automated installation step.

github-issues