The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from existing pull request descriptions. * Ingestion points: Pull request bodies are retrieved from the environment using gh pr view in SKILL.md. * Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the ingested text. * Capability inventory: The agent can write files to .artifacts/pr/body.md and execute shell commands via the GitHub CLI (gh pr create and gh pr edit) as specified in SKILL.md. * Sanitization: No input validation or sanitization is applied to the retrieved PR body before the agent processes and modifies it.
[EXTERNAL_DOWNLOADS]: The skill references external resources from well-known services and documentation sites. * Fetches badge images from img.shields.io, a standard service for repository metadata badges. * References the ai-declaration.md website for transparency standards and specification details.
[COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) to manage the pull request description lifecycle. * Executes gh pr create, gh pr edit, and gh pr view to create, modify, and read pull request data.

dsh-pr-description