The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses terminal access to run git commands, including git checkout, git add, git commit, and git push. These commands are constructed dynamically based on the agent's analysis of the current working directory.
[EXTERNAL_DOWNLOADS]: The skill uses fetch_webpage to retrieve formatting instructions from https://raw.githubusercontent.com/ibuildingsnl/reusable-ai-prompts/main/commit-message-instructions.md. This is a vendor-controlled resource belonging to the skill author.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted data which can influence its behavior.
Ingestion points: Local file content via git status and git diff, and instructions fetched from an external URL in SKILL.md.
Boundary markers: The skill lacks explicit boundary markers or instructions to ignore embedded prompts within the data it analyzes.
Capability inventory: The skill possesses powerful capabilities including arbitrary terminal execution via run_in_terminal and GitLab API interaction via mcp_gitlab_create_merge_request.
Sanitization: No sanitization or validation of the ingested content is performed before it is used to formulate commit messages or terminal commands.

create-gitlab-mr