The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute various gk (GitKraken) CLI commands to perform git operations, manage work items, and interact with issue trackers. This is the primary purpose of the skill and involves standard shell command execution.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, including git repository diffs, commit history, and issue metadata from third-party providers (GitHub, Jira, GitLab, etc.), creating a potential vector for indirect prompt injection.
Ingestion points: Data is ingested through commands like gk ai commit, gk ai pr create, and gk issue list, which read repository contents and external API data.
Boundary markers: The instructions do not specify any boundary markers or delimiters to help the agent distinguish between its instructions and potentially malicious content embedded in diffs or issues.
Capability inventory: The skill has access to the filesystem and network through the gk and git CLI tools, including the ability to write to repositories and push changes to remote servers.
Sanitization: There is no mention of sanitizing or escaping the data retrieved from external sources before the agent uses it to generate AI-driven commit messages, PR descriptions, or changelogs.

gitkraken-cli